From 38c295178b284ab49727fd0d4b3e47f5a2e10080 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Marcin=20W=C4=85troba?= <markowanga@gmail.com>
Date: Fri, 27 May 2022 03:19:08 +0200
Subject: [PATCH] Add NER processing
---
.dvc/config | 1 +
dvc.lock | 78 +
dvc.yaml | 31 +
.../luna/pipeline/dependency_provider.py | 4 +
.../luna/pipeline/spacy_ner_processing.py | 50 +
.../ner_spacy_wer_processing_task.py | 100 +
experiment/voicelab/spacy_ner_processing.py | 55 +
experiment/voicelab/voicelab_dependency.py | 4 +
.../.gitignore | 4 +
pos.ipynb | 13674 +++++++---------
10 files changed, 6531 insertions(+), 7470 deletions(-)
create mode 100644 experiment/luna/pipeline/spacy_ner_processing.py
create mode 100644 experiment/pos_processing/ner_spacy_wer_processing_task.py
create mode 100644 experiment/voicelab/spacy_ner_processing.py
diff --git a/.dvc/config b/.dvc/config
index d852f27..af475a6 100644
--- a/.dvc/config
+++ b/.dvc/config
@@ -1,6 +1,7 @@
[core]
remote = clarin-biz-asr-benchmarks
autostage = true
+ hardlink_lock = true
['remote "clarin-biz-asr-benchmarks"']
url = s3://projects/clarin-biz-asr-benchmark/dvc
endpointurl = https://s3.clarin-pl.eu
diff --git a/dvc.lock b/dvc.lock
index 1d6565c..a53bada 100644
--- a/dvc.lock
+++ b/dvc.lock
@@ -410,3 +410,81 @@ stages:
md5: abb1f6102a1de3d63d0e9e2cb797d2b9.dir
size: 17369
nfiles: 500
+ voicelab_ner_spacy_processing:
+ cmd: "PYTHONPATH=. python -u experiment/voicelab/spacy_ner_processing.py\n"
+ deps:
+ - path: experiment/voicelab/spacy_ner_processing.py
+ md5: f6a4f2e34a31d15345435e11b425b1dd
+ size: 2868
+ - path: experiment_data/dataset/voicelab_cbiz_testset_20220322
+ md5: 3c2b18e1f1f89e4c5ad7b254e472b25e.dir
+ size: 4803739404
+ nfiles: 1600
+ - path: experiment_data/pipeline/asr_benchmark_voicelab_cbiz_testset_20220322/ajn_polish_asr
+ md5: da10bb60107a86f98b2d07fef5616390.dir
+ size: 22765926
+ nfiles: 800
+ - path: experiment_data/pipeline/asr_benchmark_voicelab_cbiz_testset_20220322/gold_transcript
+ md5: 9edf1e743faa9fc3515790acb6fd8cab.dir
+ size: 21846798
+ nfiles: 800
+ - path: experiment_data/pipeline/asr_benchmark_voicelab_cbiz_testset_20220322/techmo_polish_asr
+ md5: da32e6fa9d986deddb594cb66e649864.dir
+ size: 39158267
+ nfiles: 800
+ outs:
+ - path: experiment_data/pipeline/asr_benchmark_voicelab_cbiz_testset_20220322/ner_spacy_ajn_alignment_wer_embeddings
+ md5: 742f665235ea5911b79974a06de9551e.dir
+ size: 76044699
+ nfiles: 800
+ - path: experiment_data/pipeline/asr_benchmark_voicelab_cbiz_testset_20220322/ner_spacy_ajn_metrics_wer_embeddings
+ md5: 17c5ae5ffa5b380d9be5bcc5c1f71401.dir
+ size: 27796
+ nfiles: 800
+ - path: experiment_data/pipeline/asr_benchmark_voicelab_cbiz_testset_20220322/ner_spacy_techmo_alignment_wer_embeddings
+ md5: 4b161efe4a5dcedd0dfe481ff69a74a0.dir
+ size: 28195
+ nfiles: 800
+ - path: experiment_data/pipeline/asr_benchmark_voicelab_cbiz_testset_20220322/ner_spacy_techmo_metrics_wer_embeddings
+ md5: 9161b4f164b2e1a5e5e95d1069f71377.dir
+ size: 79503990
+ nfiles: 800
+ luna_ner_spacy_processing:
+ cmd: "PYTHONPATH=. python -u experiment/luna/pipeline/spacy_ner_processing.py\n"
+ deps:
+ - path: experiment/luna/pipeline/spacy_ner_processing.py
+ md5: 95191ec772c0766911c8d297ad957778
+ size: 2855
+ - path: experiment_data/dataset/LUNA.PL
+ md5: d342155b1871e881797cf7da09d5dc3c.dir
+ size: 1578358645
+ nfiles: 4500
+ - path: experiment_data/pipeline/asr_benchmark_luna/ajn_polish_asr
+ md5: 8c080d8110e5860e78bfcb311fe2b90d.dir
+ size: 6204883
+ nfiles: 500
+ - path: experiment_data/pipeline/asr_benchmark_luna/gold_transcript
+ md5: c9c51d94294eb1b30b39aef5d6abbe4b.dir
+ size: 6706925
+ nfiles: 500
+ - path: experiment_data/pipeline/asr_benchmark_luna/techmo_polish_asr
+ md5: 3787c6a4c7941787253165e2ba760e73.dir
+ size: 9697519
+ nfiles: 500
+ outs:
+ - path: experiment_data/pipeline/asr_benchmark_luna/ner_spacy_ajn_alignment_wer_embeddings
+ md5: 79aecfe01e3ce64fef8f83de75b08bfb.dir
+ size: 21308988
+ nfiles: 500
+ - path: experiment_data/pipeline/asr_benchmark_luna/ner_spacy_ajn_metrics_wer_embeddings
+ md5: 2e136b8d41d48429267c966d5688d78a.dir
+ size: 17297
+ nfiles: 500
+ - path: experiment_data/pipeline/asr_benchmark_luna/ner_spacy_techmo_alignment_wer_embeddings
+ md5: e4948a2a68306630df0459d09ccd5ee6.dir
+ size: 17418
+ nfiles: 500
+ - path: experiment_data/pipeline/asr_benchmark_luna/ner_spacy_techmo_metrics_wer_embeddings
+ md5: ccbdbd523fb102a196abe8750cb78367.dir
+ size: 20451389
+ nfiles: 500
diff --git a/dvc.yaml b/dvc.yaml
index c34b982..6034219 100644
--- a/dvc.yaml
+++ b/dvc.yaml
@@ -72,6 +72,22 @@ stages:
- experiment_data/pipeline/asr_benchmark_luna/tag_spacy_ajn_metrics_wer_embeddings
- experiment_data/pipeline/asr_benchmark_luna/tag_spacy_ajn_alignment_wer_embeddings
+ luna_ner_spacy_processing:
+ cmd: |
+ PYTHONPATH=. python -u experiment/luna/pipeline/spacy_ner_processing.py
+ deps:
+ - experiment/luna/pipeline/spacy_ner_processing.py
+ - experiment_data/dataset/LUNA.PL
+ - experiment_data/pipeline/asr_benchmark_luna/gold_transcript
+ - experiment_data/pipeline/asr_benchmark_luna/techmo_polish_asr
+ - experiment_data/pipeline/asr_benchmark_luna/ajn_polish_asr
+ outs:
+ - experiment_data/pipeline/asr_benchmark_luna/ner_spacy_techmo_metrics_wer_embeddings
+ - experiment_data/pipeline/asr_benchmark_luna/ner_spacy_techmo_alignment_wer_embeddings
+ - experiment_data/pipeline/asr_benchmark_luna/ner_spacy_ajn_metrics_wer_embeddings
+ - experiment_data/pipeline/asr_benchmark_luna/ner_spacy_ajn_alignment_wer_embeddings
+
+
voicelab_import_to_common_format:
cmd: PYTHONPATH=. python -u experiment/voicelab/import_data.py
@@ -145,4 +161,19 @@ stages:
- experiment_data/pipeline/asr_benchmark_voicelab_cbiz_testset_20220322/tag_spacy_ajn_metrics_wer_embeddings
- experiment_data/pipeline/asr_benchmark_voicelab_cbiz_testset_20220322/tag_spacy_ajn_alignment_wer_embeddings
+ voicelab_ner_spacy_processing:
+ cmd: |
+ PYTHONPATH=. python -u experiment/voicelab/spacy_ner_processing.py
+ deps:
+ - experiment/voicelab/spacy_ner_processing.py
+ - experiment_data/dataset/voicelab_cbiz_testset_20220322
+ - experiment_data/pipeline/asr_benchmark_voicelab_cbiz_testset_20220322/gold_transcript
+ - experiment_data/pipeline/asr_benchmark_voicelab_cbiz_testset_20220322/techmo_polish_asr
+ - experiment_data/pipeline/asr_benchmark_voicelab_cbiz_testset_20220322/ajn_polish_asr
+ outs:
+ - experiment_data/pipeline/asr_benchmark_voicelab_cbiz_testset_20220322/ner_spacy_techmo_metrics_wer_embeddings
+ - experiment_data/pipeline/asr_benchmark_voicelab_cbiz_testset_20220322/ner_spacy_techmo_alignment_wer_embeddings
+ - experiment_data/pipeline/asr_benchmark_voicelab_cbiz_testset_20220322/ner_spacy_ajn_metrics_wer_embeddings
+ - experiment_data/pipeline/asr_benchmark_voicelab_cbiz_testset_20220322/ner_spacy_ajn_alignment_wer_embeddings
+
# concurrent features, multiprocessing
diff --git a/experiment/luna/pipeline/dependency_provider.py b/experiment/luna/pipeline/dependency_provider.py
index 1be90b2..edfe645 100644
--- a/experiment/luna/pipeline/dependency_provider.py
+++ b/experiment/luna/pipeline/dependency_provider.py
@@ -17,6 +17,8 @@ WORD_TECHMO_METRICS_WER_EMBEDDINGS = 'word_techmo_metrics_wer_embeddings'
WORD_TECHMO_ALIGNMENT_WER_EMBEDDINGS = 'word_techmo_alignment_wer_embeddings'
TAG_SPACY_TECHMO_METRICS_WER_EMBEDDINGS = 'tag_spacy_techmo_metrics_wer_embeddings'
TAG_SPACY_TECHMO_ALIGNMENT_WER_EMBEDDINGS = 'tag_spacy_techmo_alignment_wer_embeddings'
+NER_SPACY_TECHMO_METRICS_WER_EMBEDDINGS = 'ner_spacy_techmo_metrics_wer_embeddings'
+NER_SPACY_TECHMO_ALIGNMENT_WER_EMBEDDINGS = 'ner_spacy_techmo_alignment_wer_embeddings'
AJN_POLISH_ASR = 'ajn_polish_asr'
WORD_AJN_METRICS_WER = 'word_ajn_metrics_wer'
@@ -28,6 +30,8 @@ WORD_AJN_METRICS_WER_EMBEDDINGS = 'word_ajn_metrics_wer_embeddings'
WORD_AJN_ALIGNMENT_WER_EMBEDDINGS = 'word_ajn_alignment_wer_embeddings'
TAG_SPACY_AJN_METRICS_WER_EMBEDDINGS = 'tag_spacy_ajn_metrics_wer_embeddings'
TAG_SPACY_AJN_ALIGNMENT_WER_EMBEDDINGS = 'tag_spacy_ajn_alignment_wer_embeddings'
+NER_SPACY_AJN_METRICS_WER_EMBEDDINGS = 'ner_spacy_ajn_metrics_wer_embeddings'
+NER_SPACY_AJN_ALIGNMENT_WER_EMBEDDINGS = 'ner_spacy_ajn_alignment_wer_embeddings'
diff --git a/experiment/luna/pipeline/spacy_ner_processing.py b/experiment/luna/pipeline/spacy_ner_processing.py
new file mode 100644
index 0000000..2739ae7
--- /dev/null
+++ b/experiment/luna/pipeline/spacy_ner_processing.py
@@ -0,0 +1,50 @@
+from experiment.luna.pipeline.dependency_provider import get_record_provider, GOLD_TRANSCRIPT, TECHMO_POLISH_ASR, \
+ get_multiple_files_repository, \
+ GOLD_TRANSCRIPT_SPACY, POS_TECHMO_ALIGNMENT_WER, POS_TECHMO_METRICS_WER, WORD_TECHMO_METRICS_WER, \
+ WORD_TECHMO_ALIGNMENT_WER, TECHMO_SPACY, WORD_TECHMO_METRICS_WER_EMBEDDINGS, WORD_TECHMO_ALIGNMENT_WER_EMBEDDINGS, \
+ AJN_SPACY, TAG_SPACY_TECHMO_ALIGNMENT_WER_EMBEDDINGS, TAG_SPACY_TECHMO_METRICS_WER_EMBEDDINGS, \
+ TAG_SPACY_AJN_METRICS_WER_EMBEDDINGS, TAG_SPACY_AJN_ALIGNMENT_WER_EMBEDDINGS, \
+ NER_SPACY_TECHMO_METRICS_WER_EMBEDDINGS, NER_SPACY_TECHMO_ALIGNMENT_WER_EMBEDDINGS, AJN_POLISH_ASR, \
+ NER_SPACY_AJN_ALIGNMENT_WER_EMBEDDINGS, NER_SPACY_AJN_METRICS_WER_EMBEDDINGS
+from experiment.pos_processing.asr_spacy_token_pos_processing_task import AsrSpacyTokenPosProcessingTask
+from experiment.pos_processing.ner_spacy_wer_processing_task import NerSpacyWerProcessingTask
+from experiment.pos_processing.spacy_pos_wer_processing_task import SpacyPosWerProcessingTask
+from experiment.pos_processing.tag_spacy_wer_processing_task import TagSpacyWerProcessingTask
+from sziszapangma.core.transformer.web_embedding_transformer import WebEmbeddingTransformer
+from sziszapangma.integration.asr_processor import AsrPathCacheClient
+from sziszapangma.integration.experiment_manager import ExperimentManager
+from sziszapangma.integration.task.asr_task import AsrTask
+from sziszapangma.integration.task.classic_wer_metric_task import ClassicWerMetricTask
+from sziszapangma.integration.task.embedding_wer_metrics_task import EmbeddingWerMetricsTask
+
+
+def run_luna_experiment():
+ record_provider = get_record_provider()
+ experiment_processor = ExperimentManager(
+ record_id_iterator=record_provider,
+ processing_tasks=[
+ NerSpacyWerProcessingTask(
+ task_name='techmo_ner_wer_processing',
+ require_update=False,
+ gold_transcript_property_name=GOLD_TRANSCRIPT,
+ asr_transcript_property_name=TECHMO_POLISH_ASR,
+ ner_alignment_wer=NER_SPACY_TECHMO_METRICS_WER_EMBEDDINGS,
+ ner_metrics_wer=NER_SPACY_TECHMO_ALIGNMENT_WER_EMBEDDINGS
+ ),
+ NerSpacyWerProcessingTask(
+ task_name='ajn_ner_wer_processing',
+ require_update=False,
+ gold_transcript_property_name=GOLD_TRANSCRIPT,
+ asr_transcript_property_name=AJN_POLISH_ASR,
+ ner_alignment_wer=NER_SPACY_AJN_ALIGNMENT_WER_EMBEDDINGS,
+ ner_metrics_wer=NER_SPACY_AJN_METRICS_WER_EMBEDDINGS
+ )
+ ],
+ experiment_repository=get_multiple_files_repository(),
+ relation_manager_provider=record_provider
+ )
+ experiment_processor.process()
+
+
+if __name__ == '__main__':
+ run_luna_experiment()
diff --git a/experiment/pos_processing/ner_spacy_wer_processing_task.py b/experiment/pos_processing/ner_spacy_wer_processing_task.py
new file mode 100644
index 0000000..b8da316
--- /dev/null
+++ b/experiment/pos_processing/ner_spacy_wer_processing_task.py
@@ -0,0 +1,100 @@
+import uuid
+from typing import Any, List, Dict
+
+import spacy
+
+from sziszapangma.core.alignment.alignment_classic_calculator import AlignmentClassicCalculator
+from sziszapangma.core.alignment.alignment_step import AlignmentStep
+from sziszapangma.core.wer.wer_calculator import WerCalculator
+from sziszapangma.integration.mapper.alignment_step_mapper import AlignmentStepMapper
+from sziszapangma.integration.repository.experiment_repository import ExperimentRepository
+from sziszapangma.integration.task.processing_task import ProcessingTask
+from sziszapangma.model.model import Word
+from sziszapangma.model.relation_manager import RelationManager
+
+_CLASSIC_WER = "classic_wer"
+
+
+class NerSpacyWerProcessingTask(ProcessingTask):
+ _gold_transcript_property_name: str
+ _asr_transcript_property_name: str
+ _ner_alignment_wer: str
+ _ner_metrics_wer: str
+ _alignment_classic_calculator: AlignmentClassicCalculator
+ _wer_calculator: WerCalculator
+ _nlp = Any
+
+ def __init__(
+ self,
+ task_name: str,
+ gold_transcript_property_name: str,
+ require_update: bool,
+ asr_transcript_property_name: str,
+ ner_alignment_wer: str,
+ ner_metrics_wer: str
+ ):
+ super().__init__(task_name, require_update)
+ self._gold_transcript_property_name = gold_transcript_property_name
+ self._asr_transcript_property_name = asr_transcript_property_name
+ self._ner_alignment_wer = ner_alignment_wer
+ self._ner_metrics_wer = ner_metrics_wer
+
+ self._alignment_classic_calculator = AlignmentClassicCalculator()
+ self._wer_calculator = WerCalculator()
+
+ self._nlp = spacy.load("pl_core_news_lg")
+
+ def transcript_to_new_words(self, text: str) -> List[Word]:
+ doc = self._nlp(text)
+ arr = ['_' for _ in range(len(doc))]
+ for ent in doc.ents:
+ for itt in range(ent.start, ent.end):
+ arr[itt] = ent.label_
+ return [
+ Word(id=str(uuid.uuid4()), type='Word', text=word_text)
+ for word_text in arr
+ ]
+
+ def run_single_process(
+ self,
+ record_id: str,
+ experiment_repository: ExperimentRepository,
+ relation_manager: RelationManager,
+ ):
+ gold_transcript_text = ' '.join([it['word'] for it in experiment_repository.get_property_for_key(
+ record_id, self._gold_transcript_property_name)])
+ asr_transcript_text = experiment_repository.get_property_for_key(
+ record_id, self._asr_transcript_property_name)['full_text']
+
+ gold_ner_words = self.transcript_to_new_words(gold_transcript_text)
+ asr_ner_words = self.transcript_to_new_words(asr_transcript_text)
+
+ if gold_ner_words is not None and asr_ner_words is not None:
+ alignment_steps = self._get_alignment(gold_ner_words, asr_ner_words)
+ experiment_repository.update_property_for_key(
+ record_id,
+ self._ner_alignment_wer,
+ [AlignmentStepMapper.to_json_dict(it) for it in alignment_steps],
+ )
+ experiment_repository.update_property_for_key(
+ record_id, self._ner_metrics_wer, self.calculate_metrics(alignment_steps)
+ )
+
+ def _get_alignment(
+ self, gold_transcript: List[Word], asr_transcript: List[Word]
+ ) -> List[AlignmentStep]:
+ return self._alignment_classic_calculator.calculate_alignment(
+ reference=gold_transcript, hypothesis=asr_transcript
+ )
+
+ def calculate_metrics(self, alignment_steps: List[AlignmentStep]) -> Dict[str, Any]:
+ """Calculate all metrics for data sample."""
+ metrics = dict()
+ metrics[_CLASSIC_WER] = self._wer_calculator.calculate_wer(alignment_steps)
+ return metrics
+
+ def skip_for_record(self, record_id: str, experiment_repository: ExperimentRepository) -> bool:
+ return (
+ experiment_repository.get_property_for_key(record_id, self._ner_metrics_wer)
+ is not None
+ )
diff --git a/experiment/voicelab/spacy_ner_processing.py b/experiment/voicelab/spacy_ner_processing.py
new file mode 100644
index 0000000..99686bb
--- /dev/null
+++ b/experiment/voicelab/spacy_ner_processing.py
@@ -0,0 +1,55 @@
+from experiment.pos_processing.asr_spacy_token_pos_processing_task import AsrSpacyTokenPosProcessingTask
+from experiment.pos_processing.ner_spacy_wer_processing_task import NerSpacyWerProcessingTask
+from experiment.pos_processing.spacy_pos_wer_processing_task import SpacyPosWerProcessingTask
+from experiment.pos_processing.tag_spacy_wer_processing_task import TagSpacyWerProcessingTask
+from experiment.voicelab.voicelab_dependency import get_record_provider, get_repository, GOLD_TRANSCRIPT, \
+ GOLD_TRANSCRIPT_SPACY, TECHMO_POLISH_ASR, WORD_TECHMO_METRICS_WER, WORD_TECHMO_ALIGNMENT_WER, TECHMO_SPACY, \
+ POS_TECHMO_METRICS_WER, POS_TECHMO_ALIGNMENT_WER, WORD_TECHMO_METRICS_WER_EMBEDDINGS, \
+ WORD_TECHMO_ALIGNMENT_WER_EMBEDDINGS, TAG_SPACY_TECHMO_ALIGNMENT_WER_EMBEDDINGS, \
+ TAG_SPACY_TECHMO_METRICS_WER_EMBEDDINGS, AJN_SPACY, TAG_SPACY_AJN_ALIGNMENT_WER_EMBEDDINGS, \
+ TAG_SPACY_AJN_METRICS_WER_EMBEDDINGS, NER_SPACY_TECHMO_METRICS_WER_EMBEDDINGS, \
+ NER_SPACY_TECHMO_ALIGNMENT_WER_EMBEDDINGS, AJN_POLISH_ASR, NER_SPACY_AJN_ALIGNMENT_WER_EMBEDDINGS, \
+ NER_SPACY_AJN_METRICS_WER_EMBEDDINGS
+from sziszapangma.core.transformer.web_embedding_transformer import WebEmbeddingTransformer
+from sziszapangma.integration.asr_processor import AsrPathCacheClient
+from sziszapangma.integration.experiment_manager import ExperimentManager
+from sziszapangma.integration.task.asr_task import AsrTask
+from sziszapangma.integration.task.classic_wer_metric_task import ClassicWerMetricTask
+from sziszapangma.integration.task.embedding_wer_metrics_task import EmbeddingWerMetricsTask
+
+
+def run_voicelab_experiment():
+ record_provider = get_record_provider()
+ experiment_processor = ExperimentManager(
+ record_id_iterator=record_provider,
+ processing_tasks=[
+ NerSpacyWerProcessingTask(
+ task_name='techmo_ner_wer_processing',
+ require_update=False,
+ gold_transcript_property_name=GOLD_TRANSCRIPT,
+ asr_transcript_property_name=TECHMO_POLISH_ASR,
+ ner_alignment_wer=NER_SPACY_TECHMO_METRICS_WER_EMBEDDINGS,
+ ner_metrics_wer=NER_SPACY_TECHMO_ALIGNMENT_WER_EMBEDDINGS
+ ),
+ NerSpacyWerProcessingTask(
+ task_name='ajn_ner_wer_processing',
+ require_update=False,
+ gold_transcript_property_name=GOLD_TRANSCRIPT,
+ asr_transcript_property_name=AJN_POLISH_ASR,
+ ner_alignment_wer=NER_SPACY_AJN_ALIGNMENT_WER_EMBEDDINGS,
+ ner_metrics_wer=NER_SPACY_AJN_METRICS_WER_EMBEDDINGS
+ )
+
+ ],
+ experiment_repository=get_repository(),
+ relation_manager_provider=record_provider
+ )
+ experiment_processor.process()
+
+
+def example_run():
+ run_voicelab_experiment()
+
+
+if __name__ == '__main__':
+ example_run()
diff --git a/experiment/voicelab/voicelab_dependency.py b/experiment/voicelab/voicelab_dependency.py
index ca1293c..28b8f29 100644
--- a/experiment/voicelab/voicelab_dependency.py
+++ b/experiment/voicelab/voicelab_dependency.py
@@ -17,6 +17,8 @@ WORD_TECHMO_METRICS_WER_EMBEDDINGS = 'word_techmo_metrics_wer_embeddings'
WORD_TECHMO_ALIGNMENT_WER_EMBEDDINGS = 'word_techmo_alignment_wer_embeddings'
TAG_SPACY_TECHMO_METRICS_WER_EMBEDDINGS = 'tag_spacy_techmo_metrics_wer_embeddings'
TAG_SPACY_TECHMO_ALIGNMENT_WER_EMBEDDINGS = 'tag_spacy_techmo_alignment_wer_embeddings'
+NER_SPACY_TECHMO_METRICS_WER_EMBEDDINGS = 'ner_spacy_techmo_metrics_wer_embeddings'
+NER_SPACY_TECHMO_ALIGNMENT_WER_EMBEDDINGS = 'ner_spacy_techmo_alignment_wer_embeddings'
AJN_POLISH_ASR = 'ajn_polish_asr'
WORD_AJN_METRICS_WER = 'word_ajn_metrics_wer'
@@ -28,6 +30,8 @@ WORD_AJN_METRICS_WER_EMBEDDINGS = 'word_ajn_metrics_wer_embeddings'
WORD_AJN_ALIGNMENT_WER_EMBEDDINGS = 'word_ajn_alignment_wer_embeddings'
TAG_SPACY_AJN_METRICS_WER_EMBEDDINGS = 'tag_spacy_ajn_metrics_wer_embeddings'
TAG_SPACY_AJN_ALIGNMENT_WER_EMBEDDINGS = 'tag_spacy_ajn_alignment_wer_embeddings'
+NER_SPACY_AJN_METRICS_WER_EMBEDDINGS = 'ner_spacy_ajn_metrics_wer_embeddings'
+NER_SPACY_AJN_ALIGNMENT_WER_EMBEDDINGS = 'ner_spacy_ajn_alignment_wer_embeddings'
PIPELINE_DATA_DIRECTORY = 'experiment_data/pipeline'
EXPERIMENT_NAME = 'asr_benchmark_voicelab_cbiz_testset_20220322'
diff --git a/experiment_data/pipeline/asr_benchmark_voicelab_cbiz_testset_20220322/.gitignore b/experiment_data/pipeline/asr_benchmark_voicelab_cbiz_testset_20220322/.gitignore
index 0b94428..2afde86 100644
--- a/experiment_data/pipeline/asr_benchmark_voicelab_cbiz_testset_20220322/.gitignore
+++ b/experiment_data/pipeline/asr_benchmark_voicelab_cbiz_testset_20220322/.gitignore
@@ -20,3 +20,7 @@
/tag_spacy_techmo_alignment_wer_embeddings
/tag_spacy_ajn_metrics_wer_embeddings
/tag_spacy_ajn_alignment_wer_embeddings
+/ner_spacy_techmo_metrics_wer_embeddings
+/ner_spacy_techmo_alignment_wer_embeddings
+/ner_spacy_ajn_metrics_wer_embeddings
+/ner_spacy_ajn_alignment_wer_embeddings
diff --git a/pos.ipynb b/pos.ipynb
index bac442b..3b6dbb9 100644
--- a/pos.ipynb
+++ b/pos.ipynb
@@ -10,7 +10,7 @@
},
{
"cell_type": "code",
- "execution_count": 26,
+ "execution_count": 2,
"id": "1929f9bb-5060-4530-811b-823d69a5b00f",
"metadata": {},
"outputs": [],
@@ -32,7 +32,7 @@
},
{
"cell_type": "code",
- "execution_count": 27,
+ "execution_count": 3,
"id": "321a93d9-0c5d-4d42-ba8f-4b704a05d78c",
"metadata": {},
"outputs": [],
@@ -50,7 +50,7 @@
},
{
"cell_type": "code",
- "execution_count": 28,
+ "execution_count": 4,
"id": "bbe2a7bf-bb6d-42ee-b5ce-48e6ec7fcd94",
"metadata": {},
"outputs": [],
@@ -61,7 +61,7 @@
},
{
"cell_type": "code",
- "execution_count": 29,
+ "execution_count": 9,
"id": "4bb1a1c0-8784-4e0d-9426-13495718e087",
"metadata": {},
"outputs": [],
@@ -78,6 +78,8 @@
"POS_TECHMO_METRICS_WER = 'pos_techmo_metrics_wer'\n",
"TAG_SPACY_TECHMO_METRICS_WER_EMBEDDINGS = 'tag_spacy_techmo_metrics_wer_embeddings'\n",
"TAG_SPACY_TECHMO_ALIGNMENT_WER_EMBEDDINGS = 'tag_spacy_techmo_alignment_wer_embeddings'\n",
+ "NER_SPACY_TECHMO_METRICS_WER_EMBEDDINGS = 'ner_spacy_techmo_metrics_wer_embeddings'\n",
+ "NER_SPACY_TECHMO_ALIGNMENT_WER_EMBEDDINGS = 'ner_spacy_techmo_alignment_wer_embeddings'\n",
"\n",
"AJN_POLISH_ASR = 'ajn_polish_asr'\n",
"WORD_AJN_MERTICS_WER = 'word_ajn_metrics_wer'\n",
@@ -86,12 +88,14 @@
"POS_AJN_ALIGNMENT_WER = 'pos_ajn_metrics_wer'\n",
"POS_AJN_METRICS_WER = 'pos_ajn_alignment_wer'\n",
"TAG_SPACY_AJN_METRICS_WER_EMBEDDINGS = 'tag_spacy_ajn_metrics_wer_embeddings'\n",
- "TAG_SPACY_AJN_ALIGNMENT_WER_EMBEDDINGS = 'tag_spacy_ajn_alignment_wer_embeddings'"
+ "TAG_SPACY_AJN_ALIGNMENT_WER_EMBEDDINGS = 'tag_spacy_ajn_alignment_wer_embeddings'\n",
+ "NER_SPACY_AJN_METRICS_WER_EMBEDDINGS = 'ner_spacy_ajn_metrics_wer_embeddings'\n",
+ "NER_SPACY_AJN_ALIGNMENT_WER_EMBEDDINGS = 'ner_spacy_ajn_alignment_wer_embeddings'"
]
},
{
"cell_type": "code",
- "execution_count": 30,
+ "execution_count": 10,
"id": "d4265253-755a-4160-97f7-72604fdf41d1",
"metadata": {},
"outputs": [],
@@ -108,12 +112,14 @@
" pos_asr_metric_wer: str\n",
" pos_asr_alignment_wer: str\n",
" tag_metric_wer: str\n",
- " tag_alignment_wer: str"
+ " tag_alignment_wer: str\n",
+ " ner_metric_wer: str\n",
+ " ner_alignment_wer: str"
]
},
{
"cell_type": "code",
- "execution_count": 31,
+ "execution_count": 11,
"id": "950b0bb8-e5ae-46e0-97a2-a832b7c8a70f",
"metadata": {},
"outputs": [],
@@ -129,7 +135,9 @@
" pos_asr_metric_wer=POS_TECHMO_METRICS_WER,\n",
" pos_asr_alignment_wer=POS_TECHMO_ALIGNMENT_WER,\n",
" tag_metric_wer=TAG_SPACY_TECHMO_METRICS_WER_EMBEDDINGS,\n",
- " tag_alignment_wer=TAG_SPACY_TECHMO_ALIGNMENT_WER_EMBEDDINGS\n",
+ " tag_alignment_wer=TAG_SPACY_TECHMO_ALIGNMENT_WER_EMBEDDINGS,\n",
+ " ner_metric_wer=NER_SPACY_TECHMO_METRICS_WER_EMBEDDINGS,\n",
+ " ner_alignment_wer=NER_SPACY_TECHMO_ALIGNMENT_WER_EMBEDDINGS\n",
")\n",
"ajn_connections_config = CollectionsConfig(\n",
" config_name='AJN ASR',\n",
@@ -142,13 +150,15 @@
" pos_asr_metric_wer=POS_AJN_ALIGNMENT_WER,\n",
" pos_asr_alignment_wer=POS_AJN_METRICS_WER,\n",
" tag_metric_wer=TAG_SPACY_AJN_METRICS_WER_EMBEDDINGS,\n",
- " tag_alignment_wer=TAG_SPACY_AJN_ALIGNMENT_WER_EMBEDDINGS\n",
+ " tag_alignment_wer=TAG_SPACY_AJN_ALIGNMENT_WER_EMBEDDINGS,\n",
+ " ner_metric_wer=NER_SPACY_TECHMO_METRICS_WER_EMBEDDINGS,\n",
+ " ner_alignment_wer=NER_SPACY_TECHMO_ALIGNMENT_WER_EMBEDDINGS\n",
")"
]
},
{
"cell_type": "code",
- "execution_count": 32,
+ "execution_count": 12,
"id": "4dec626b-02e4-4c78-a238-04ef2f090ea5",
"metadata": {},
"outputs": [
@@ -176,7 +186,7 @@
},
{
"cell_type": "code",
- "execution_count": 33,
+ "execution_count": 13,
"id": "98c6ff1d-4fbd-4b68-9e23-ecea33852b12",
"metadata": {},
"outputs": [],
@@ -194,7 +204,7 @@
},
{
"cell_type": "code",
- "execution_count": 34,
+ "execution_count": 14,
"id": "5bd3dcd6-6b32-480c-8937-07c770354ed1",
"metadata": {},
"outputs": [],
@@ -241,7 +251,7 @@
},
{
"cell_type": "code",
- "execution_count": 35,
+ "execution_count": 23,
"id": "74bf17ba-8572-4758-8116-794708b6ea08",
"metadata": {},
"outputs": [],
@@ -316,6 +326,23 @@
" for it in word_alignment_wer\n",
" ]\n",
" return pd.DataFrame(arr)\n",
+ "\n",
+ "\n",
+ "def get_ner_alignment_df(record_id: str, experiment_repository: ExperimentRepository, \n",
+ " collections_config: CollectionsConfig) -> pd.DataFrame:\n",
+ " word_alignment_wer = experiment_repository.get_property_for_key(record_id, \n",
+ " collections_config.ner_metric_wer)\n",
+ " arr = [\n",
+ " {\n",
+ " 'step_type': it['step_type'],\n",
+ " 'reference_word_text': it['step_words']['reference_word']['text'] \n",
+ " if 'reference_word' in it['step_words'] else '',\n",
+ " 'hypothesis_word_text': it['step_words']['hypothesis_word']['text']\n",
+ " if 'hypothesis_word' in it['step_words'] else '',\n",
+ " }\n",
+ " for it in word_alignment_wer\n",
+ " ]\n",
+ " return pd.DataFrame(arr)\n",
" \n",
" \n",
"def show_report_for(record_id: str, experiment_repository: ExperimentRepository,\n",
@@ -331,13 +358,17 @@
" print()\n",
" print(f\"pos wer {experiment_repository.get_property_for_key(record_id, collections_config.pos_asr_metric_wer)}\")\n",
" print()\n",
- " print(f\"tag wer {experiment_repository.get_property_for_key(record_id, collections_config.tag_metric_wer)}\")\n",
+ " print(f\"tag wer {experiment_repository.get_property_for_key(record_id, collections_config.tag_metric_wer)}\") \n",
+ " print()\n",
+ " print(f\"ner wer {experiment_repository.get_property_for_key(record_id, collections_config.ner_alignment_wer)}\")\n",
" print()\n",
" display(get_word_alignment_df(record_id, experiment_repository, collections_config))\n",
" print()\n",
" display(get_pos_alignment_df(record_id, experiment_repository, collections_config))\n",
" print()\n",
" display(get_tag_alignment_df(record_id, experiment_repository, collections_config))\n",
+ " print()\n",
+ " display(get_ner_alignment_df(record_id, experiment_repository, collections_config))\n",
" print('--------------------------------------------------------------')\n",
" print('--------------------------------------------------------------')\n",
" print('--------------------------------------------------------------')"
@@ -353,7 +384,7 @@
},
{
"cell_type": "code",
- "execution_count": 36,
+ "execution_count": 24,
"id": "3395e091-3488-4b49-aede-af15a0055a8b",
"metadata": {},
"outputs": [
@@ -361,18 +392,20 @@
"name": "stdout",
"output_type": "stream",
"text": [
- "record_id: LUNA.PL__JAKDOJECHAC__DOBRAJAKOSC__F__2_2007-03-26_12_22_36__2_2007-03-26_12_22_36\n",
+ "record_id: LUNA.PL__PRZYSTANKI__DOBRAJAKOSC__M__1_2007-03-30_14_37_38__1_2007-03-30_14_37_38\n",
"properties_confiog: TECHMO ASR\n",
"\n",
- "gold transcript: xxx dzień dobry dzień dobry proszę pana ja chciałam się dowiedzieć bo nie bardzo wiem gdzie znajduje się ulica Zwierzyniecka i jak dojechać z Bródna na przykład ? na Zwierzyniecką na Zwierzyniecką a z Bródna z którego miejsca ? z Bródna to jest ulica Wyszogrodzka tu przy Rembielińskiej czyli przy tramwajach tak ? przy tramwajach tak może pani poczeka sprawdzę dobrze dobrze pani sobie podjedzie tramwajem do Ronda Żaba tak od Ronda Żaba już sto sześćdziesiąt dwa jest sto sześćdziesiąt dwa tak i sto sześćdziesiąt dwa tam dojadę do tej ulicy tak może pani wysiąść na przystanku Bartycka albo Sielce Bartycka albo ? Sielce Sielce tak ? tak aha i tam w pobliżu jest ta ulica tak ? a Zwierzyniecka wysoki numer ma pani ? Zwierzyniecka zaraz momencik osiem A Zwierzyniecka to to przy Sielce trza wysiąść przy Sielce tak ? tak przystanek Sielce aha tak no dobrze a Sielce to znaczy jaka to już jest dzielnica to ta jest przy ulica Gagarina a przy ulicy Gagarina czyli to jest tam Mokotów po prostu tak ? tak Siekierki Mokotów a Siekierki Mokotów i tam jak pani wysiądzie to trza wejść w lewo w ulicę Nehru i od Nehru odchodzi Zwierzyniecka w lewo w lewo i ulica Nehru ? tak Nehru dobrze dziękuję panu bardzo proszę do widzenia do widzenia\n",
+ "gold transcript: xxx dzień dobry dzień dobry proszę pana ja mam o której będzie sto czterdzieści trzy będzie najbliższy z Alei Alei Witosa w stronę Gocławia z tego przystanku vis-a-vis ZUSu tak ? no nie nie tam vis-a-vis Panoramy przez Siekierkowski tam w stronę Gocławia ale to nie z tego przystanku Aleja Witosa ? no to jest czy Bartoszka na żądanie wie pan gdzie jest się zaczyna Most Siekierkowski tam w stronę Gocławia gdzie ma on przystanek pierwszy sto czterdzieści trzy znaczy tak naprawdę Most Siekierkowski to się zaczyna za Siekierki Sanktuarium no właśnie przed tym przed tym przystanek o której jest sto czterdzieści trzy najbliższy aha czyli to wtedy przystanek Małe Siekierki ale to nie jest tak tak tak tak na wysokości Panoramy aha dobrze najbliższy już chwileczkę czternasta czterdzieści sześć piętnasta zero jeden aha no dobrze dziękuję do widzenia do widzenia\n",
+ "\n",
+ "asr transcript: dzień dobry dzień dobry proszę pana ja mam pytanie o której będzie 143 będzie najbliższy z alei witosa alei witosa w stronę gocławia przystanku widzowi zusu tak no nie nie tam widzowi panoramy przez siekierkowski tam w stronę gocławia ale to nie z tego przystanku aleja witosa no to jest czy bartoszka na żądanie wie pan gdzie jest się zaczyna most siekierkowski tam w stronę wrocław on przystanek pierwszy 143 znaczy tak naprawdę most siekierkowski to się zaczyna za siekierki sanktuarium no właśnie przed tym przed tym przystanek o której jest 143 najbliższy wtedy przystanek małe siekierki ale to nie jest dokonać panoramy dobrze najbliższy już chwileczkę czternasta 46 piętnasta 0 1 aha dobrze dziękuję do widzenia\n",
"\n",
- "asr transcript: dzień dobry dzień dobry proszę pana ja chciałam się dowiedzieć bo nie bardzo wiem gdzie znajduje się ulica zwierzyniecka i jak dojechać z bródna na zwierzyniecką na zwierzyniecką ja z bródna z którego miejsca z bródna to jest ulica wyszogrodzka tu przy rembielińskiej czyli przy tramwajach przy tramwajach tak może sprawdzę dobrze dobrze podjedzie tramwajem do ronda żaba tak od ronda żaba już 162 jest 162 tak i 162 tam dojadę do tej uli tak może pani wysiąść banku bartycka albo sielce bartycka albo sielce sielce tak tak aha i tam w pobliżu jest ta ulica zwierzyniecka ma pani zwierzyniecka telefonem dzikie który 8 a zwierzyniecka to to przy sielce trza wysiąść przy sielce tak tak stanek sielce aha no dobrze a sielce jaka to już jest dzielnica to ta jest przy ulica gagarina a przy ulicy gagarina czyli to jest tam mokotów po prostu tak tak siekierki mokot siekierki mokot ów i tam jak pani wysiądzie to trza wejść scenerii i od nehru odchodzi zwierzyniecka w le w lewo i ulica nehru tak nehru dobrze dziękuję panu bardzo do widzenia to wszystko\n",
+ "word wer {'classic_wer': 0.41134751773049644}\n",
"\n",
- "word wer {'classic_wer': 0.4018264840182648}\n",
+ "pos wer {'classic_wer': 0.3624161073825503}\n",
"\n",
- "pos wer {'classic_wer': 0.3059360730593607}\n",
+ "tag wer {'classic_wer': 0.4429530201342282}\n",
"\n",
- "tag wer {'classic_wer': 0.4018264840182648}\n",
+ "ner wer {'classic_wer': 0.22818791946308725}\n",
"\n"
]
},
@@ -454,422 +487,422 @@
" <tr>\n",
" <th>8</th>\n",
" <td>CORRECT</td>\n",
- " <td>chciałam</td>\n",
- " <td>chciałam</td>\n",
+ " <td>mam</td>\n",
+ " <td>mam</td>\n",
" </tr>\n",
" <tr>\n",
" <th>9</th>\n",
- " <td>CORRECT</td>\n",
- " <td>siÄ™</td>\n",
- " <td>siÄ™</td>\n",
+ " <td>INSERTION</td>\n",
+ " <td></td>\n",
+ " <td>pytanie</td>\n",
" </tr>\n",
" <tr>\n",
" <th>10</th>\n",
" <td>CORRECT</td>\n",
- " <td>dowiedzieć</td>\n",
- " <td>dowiedzieć</td>\n",
+ " <td>o</td>\n",
+ " <td>o</td>\n",
" </tr>\n",
" <tr>\n",
" <th>11</th>\n",
" <td>CORRECT</td>\n",
- " <td>bo</td>\n",
- " <td>bo</td>\n",
+ " <td>której</td>\n",
+ " <td>której</td>\n",
" </tr>\n",
" <tr>\n",
" <th>12</th>\n",
" <td>CORRECT</td>\n",
- " <td>nie</td>\n",
- " <td>nie</td>\n",
+ " <td>będzie</td>\n",
+ " <td>będzie</td>\n",
" </tr>\n",
" <tr>\n",
" <th>13</th>\n",
- " <td>CORRECT</td>\n",
- " <td>bardzo</td>\n",
- " <td>bardzo</td>\n",
+ " <td>DELETION</td>\n",
+ " <td>sto</td>\n",
+ " <td></td>\n",
" </tr>\n",
" <tr>\n",
" <th>14</th>\n",
- " <td>CORRECT</td>\n",
- " <td>wiem</td>\n",
- " <td>wiem</td>\n",
+ " <td>DELETION</td>\n",
+ " <td>czterdzieści</td>\n",
+ " <td></td>\n",
" </tr>\n",
" <tr>\n",
" <th>15</th>\n",
- " <td>CORRECT</td>\n",
- " <td>gdzie</td>\n",
- " <td>gdzie</td>\n",
+ " <td>SUBSTITUTION</td>\n",
+ " <td>trzy</td>\n",
+ " <td>143</td>\n",
" </tr>\n",
" <tr>\n",
" <th>16</th>\n",
" <td>CORRECT</td>\n",
- " <td>znajduje</td>\n",
- " <td>znajduje</td>\n",
+ " <td>będzie</td>\n",
+ " <td>będzie</td>\n",
" </tr>\n",
" <tr>\n",
" <th>17</th>\n",
" <td>CORRECT</td>\n",
- " <td>siÄ™</td>\n",
- " <td>siÄ™</td>\n",
+ " <td>najbliższy</td>\n",
+ " <td>najbliższy</td>\n",
" </tr>\n",
" <tr>\n",
" <th>18</th>\n",
" <td>CORRECT</td>\n",
- " <td>ulica</td>\n",
- " <td>ulica</td>\n",
+ " <td>z</td>\n",
+ " <td>z</td>\n",
" </tr>\n",
" <tr>\n",
" <th>19</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>Zwierzyniecka</td>\n",
- " <td>zwierzyniecka</td>\n",
+ " <td>INSERTION</td>\n",
+ " <td></td>\n",
+ " <td>alei</td>\n",
" </tr>\n",
" <tr>\n",
" <th>20</th>\n",
- " <td>CORRECT</td>\n",
- " <td>i</td>\n",
- " <td>i</td>\n",
+ " <td>SUBSTITUTION</td>\n",
+ " <td>Alei</td>\n",
+ " <td>witosa</td>\n",
" </tr>\n",
" <tr>\n",
" <th>21</th>\n",
- " <td>CORRECT</td>\n",
- " <td>jak</td>\n",
- " <td>jak</td>\n",
+ " <td>SUBSTITUTION</td>\n",
+ " <td>Alei</td>\n",
+ " <td>alei</td>\n",
" </tr>\n",
" <tr>\n",
" <th>22</th>\n",
- " <td>CORRECT</td>\n",
- " <td>dojechać</td>\n",
- " <td>dojechać</td>\n",
+ " <td>SUBSTITUTION</td>\n",
+ " <td>Witosa</td>\n",
+ " <td>witosa</td>\n",
" </tr>\n",
" <tr>\n",
" <th>23</th>\n",
" <td>CORRECT</td>\n",
- " <td>z</td>\n",
- " <td>z</td>\n",
+ " <td>w</td>\n",
+ " <td>w</td>\n",
" </tr>\n",
" <tr>\n",
" <th>24</th>\n",
- " <td>DELETION</td>\n",
- " <td>Bródna</td>\n",
- " <td></td>\n",
+ " <td>CORRECT</td>\n",
+ " <td>stronÄ™</td>\n",
+ " <td>stronÄ™</td>\n",
" </tr>\n",
" <tr>\n",
" <th>25</th>\n",
" <td>DELETION</td>\n",
- " <td>na</td>\n",
+ " <td>Gocławia</td>\n",
" <td></td>\n",
" </tr>\n",
" <tr>\n",
" <th>26</th>\n",
" <td>DELETION</td>\n",
- " <td>przykład</td>\n",
+ " <td>z</td>\n",
" <td></td>\n",
" </tr>\n",
" <tr>\n",
" <th>27</th>\n",
" <td>SUBSTITUTION</td>\n",
- " <td>?</td>\n",
- " <td>bródna</td>\n",
+ " <td>tego</td>\n",
+ " <td>gocławia</td>\n",
" </tr>\n",
" <tr>\n",
" <th>28</th>\n",
" <td>CORRECT</td>\n",
- " <td>na</td>\n",
- " <td>na</td>\n",
+ " <td>przystanku</td>\n",
+ " <td>przystanku</td>\n",
" </tr>\n",
" <tr>\n",
" <th>29</th>\n",
" <td>SUBSTITUTION</td>\n",
- " <td>ZwierzynieckÄ…</td>\n",
- " <td>zwierzynieckÄ…</td>\n",
+ " <td>vis-a-vis</td>\n",
+ " <td>widzowi</td>\n",
" </tr>\n",
" <tr>\n",
" <th>30</th>\n",
- " <td>CORRECT</td>\n",
- " <td>na</td>\n",
- " <td>na</td>\n",
+ " <td>SUBSTITUTION</td>\n",
+ " <td>ZUSu</td>\n",
+ " <td>zusu</td>\n",
" </tr>\n",
" <tr>\n",
" <th>31</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>ZwierzynieckÄ…</td>\n",
- " <td>zwierzynieckÄ…</td>\n",
+ " <td>CORRECT</td>\n",
+ " <td>tak</td>\n",
+ " <td>tak</td>\n",
" </tr>\n",
" <tr>\n",
" <th>32</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>a</td>\n",
- " <td>ja</td>\n",
+ " <td>DELETION</td>\n",
+ " <td>?</td>\n",
+ " <td></td>\n",
" </tr>\n",
" <tr>\n",
" <th>33</th>\n",
" <td>CORRECT</td>\n",
- " <td>z</td>\n",
- " <td>z</td>\n",
+ " <td>no</td>\n",
+ " <td>no</td>\n",
" </tr>\n",
" <tr>\n",
" <th>34</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>Bródna</td>\n",
- " <td>bródna</td>\n",
+ " <td>CORRECT</td>\n",
+ " <td>nie</td>\n",
+ " <td>nie</td>\n",
" </tr>\n",
" <tr>\n",
" <th>35</th>\n",
" <td>CORRECT</td>\n",
- " <td>z</td>\n",
- " <td>z</td>\n",
+ " <td>nie</td>\n",
+ " <td>nie</td>\n",
" </tr>\n",
" <tr>\n",
" <th>36</th>\n",
" <td>CORRECT</td>\n",
- " <td>którego</td>\n",
- " <td>którego</td>\n",
+ " <td>tam</td>\n",
+ " <td>tam</td>\n",
" </tr>\n",
" <tr>\n",
" <th>37</th>\n",
- " <td>CORRECT</td>\n",
- " <td>miejsca</td>\n",
- " <td>miejsca</td>\n",
+ " <td>SUBSTITUTION</td>\n",
+ " <td>vis-a-vis</td>\n",
+ " <td>widzowi</td>\n",
" </tr>\n",
" <tr>\n",
" <th>38</th>\n",
- " <td>DELETION</td>\n",
- " <td>?</td>\n",
- " <td></td>\n",
+ " <td>SUBSTITUTION</td>\n",
+ " <td>Panoramy</td>\n",
+ " <td>panoramy</td>\n",
" </tr>\n",
" <tr>\n",
" <th>39</th>\n",
" <td>CORRECT</td>\n",
- " <td>z</td>\n",
- " <td>z</td>\n",
+ " <td>przez</td>\n",
+ " <td>przez</td>\n",
" </tr>\n",
" <tr>\n",
" <th>40</th>\n",
" <td>SUBSTITUTION</td>\n",
- " <td>Bródna</td>\n",
- " <td>bródna</td>\n",
+ " <td>Siekierkowski</td>\n",
+ " <td>siekierkowski</td>\n",
" </tr>\n",
" <tr>\n",
" <th>41</th>\n",
" <td>CORRECT</td>\n",
- " <td>to</td>\n",
- " <td>to</td>\n",
+ " <td>tam</td>\n",
+ " <td>tam</td>\n",
" </tr>\n",
" <tr>\n",
" <th>42</th>\n",
" <td>CORRECT</td>\n",
- " <td>jest</td>\n",
- " <td>jest</td>\n",
+ " <td>w</td>\n",
+ " <td>w</td>\n",
" </tr>\n",
" <tr>\n",
" <th>43</th>\n",
" <td>CORRECT</td>\n",
- " <td>ulica</td>\n",
- " <td>ulica</td>\n",
+ " <td>stronÄ™</td>\n",
+ " <td>stronÄ™</td>\n",
" </tr>\n",
" <tr>\n",
" <th>44</th>\n",
" <td>SUBSTITUTION</td>\n",
- " <td>Wyszogrodzka</td>\n",
- " <td>wyszogrodzka</td>\n",
+ " <td>Gocławia</td>\n",
+ " <td>gocławia</td>\n",
" </tr>\n",
" <tr>\n",
" <th>45</th>\n",
" <td>CORRECT</td>\n",
- " <td>tu</td>\n",
- " <td>tu</td>\n",
+ " <td>ale</td>\n",
+ " <td>ale</td>\n",
" </tr>\n",
" <tr>\n",
" <th>46</th>\n",
" <td>CORRECT</td>\n",
- " <td>przy</td>\n",
- " <td>przy</td>\n",
+ " <td>to</td>\n",
+ " <td>to</td>\n",
" </tr>\n",
" <tr>\n",
" <th>47</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>Rembielińskiej</td>\n",
- " <td>rembielińskiej</td>\n",
+ " <td>CORRECT</td>\n",
+ " <td>nie</td>\n",
+ " <td>nie</td>\n",
" </tr>\n",
" <tr>\n",
" <th>48</th>\n",
" <td>CORRECT</td>\n",
- " <td>czyli</td>\n",
- " <td>czyli</td>\n",
+ " <td>z</td>\n",
+ " <td>z</td>\n",
" </tr>\n",
" <tr>\n",
" <th>49</th>\n",
" <td>CORRECT</td>\n",
- " <td>przy</td>\n",
- " <td>przy</td>\n",
+ " <td>tego</td>\n",
+ " <td>tego</td>\n",
" </tr>\n",
" <tr>\n",
" <th>50</th>\n",
" <td>CORRECT</td>\n",
- " <td>tramwajach</td>\n",
- " <td>tramwajach</td>\n",
+ " <td>przystanku</td>\n",
+ " <td>przystanku</td>\n",
" </tr>\n",
" <tr>\n",
" <th>51</th>\n",
" <td>DELETION</td>\n",
- " <td>tak</td>\n",
+ " <td>Aleja</td>\n",
" <td></td>\n",
" </tr>\n",
" <tr>\n",
" <th>52</th>\n",
- " <td>DELETION</td>\n",
- " <td>?</td>\n",
- " <td></td>\n",
+ " <td>SUBSTITUTION</td>\n",
+ " <td>Witosa</td>\n",
+ " <td>aleja</td>\n",
" </tr>\n",
" <tr>\n",
" <th>53</th>\n",
- " <td>CORRECT</td>\n",
- " <td>przy</td>\n",
- " <td>przy</td>\n",
+ " <td>SUBSTITUTION</td>\n",
+ " <td>?</td>\n",
+ " <td>witosa</td>\n",
" </tr>\n",
" <tr>\n",
" <th>54</th>\n",
" <td>CORRECT</td>\n",
- " <td>tramwajach</td>\n",
- " <td>tramwajach</td>\n",
+ " <td>no</td>\n",
+ " <td>no</td>\n",
" </tr>\n",
" <tr>\n",
" <th>55</th>\n",
" <td>CORRECT</td>\n",
- " <td>tak</td>\n",
- " <td>tak</td>\n",
+ " <td>to</td>\n",
+ " <td>to</td>\n",
" </tr>\n",
" <tr>\n",
" <th>56</th>\n",
" <td>CORRECT</td>\n",
- " <td>może</td>\n",
- " <td>może</td>\n",
+ " <td>jest</td>\n",
+ " <td>jest</td>\n",
" </tr>\n",
" <tr>\n",
" <th>57</th>\n",
- " <td>DELETION</td>\n",
- " <td>pani</td>\n",
- " <td></td>\n",
+ " <td>CORRECT</td>\n",
+ " <td>czy</td>\n",
+ " <td>czy</td>\n",
" </tr>\n",
" <tr>\n",
" <th>58</th>\n",
- " <td>DELETION</td>\n",
- " <td>poczeka</td>\n",
- " <td></td>\n",
+ " <td>SUBSTITUTION</td>\n",
+ " <td>Bartoszka</td>\n",
+ " <td>bartoszka</td>\n",
" </tr>\n",
" <tr>\n",
" <th>59</th>\n",
" <td>CORRECT</td>\n",
- " <td>sprawdzÄ™</td>\n",
- " <td>sprawdzÄ™</td>\n",
+ " <td>na</td>\n",
+ " <td>na</td>\n",
" </tr>\n",
" <tr>\n",
" <th>60</th>\n",
" <td>CORRECT</td>\n",
- " <td>dobrze</td>\n",
- " <td>dobrze</td>\n",
+ " <td>żądanie</td>\n",
+ " <td>żądanie</td>\n",
" </tr>\n",
" <tr>\n",
" <th>61</th>\n",
" <td>CORRECT</td>\n",
- " <td>dobrze</td>\n",
- " <td>dobrze</td>\n",
+ " <td>wie</td>\n",
+ " <td>wie</td>\n",
" </tr>\n",
" <tr>\n",
" <th>62</th>\n",
- " <td>DELETION</td>\n",
- " <td>pani</td>\n",
- " <td></td>\n",
+ " <td>CORRECT</td>\n",
+ " <td>pan</td>\n",
+ " <td>pan</td>\n",
" </tr>\n",
" <tr>\n",
" <th>63</th>\n",
- " <td>DELETION</td>\n",
- " <td>sobie</td>\n",
- " <td></td>\n",
+ " <td>CORRECT</td>\n",
+ " <td>gdzie</td>\n",
+ " <td>gdzie</td>\n",
" </tr>\n",
" <tr>\n",
" <th>64</th>\n",
" <td>CORRECT</td>\n",
- " <td>podjedzie</td>\n",
- " <td>podjedzie</td>\n",
+ " <td>jest</td>\n",
+ " <td>jest</td>\n",
" </tr>\n",
" <tr>\n",
" <th>65</th>\n",
" <td>CORRECT</td>\n",
- " <td>tramwajem</td>\n",
- " <td>tramwajem</td>\n",
+ " <td>siÄ™</td>\n",
+ " <td>siÄ™</td>\n",
" </tr>\n",
" <tr>\n",
" <th>66</th>\n",
" <td>CORRECT</td>\n",
- " <td>do</td>\n",
- " <td>do</td>\n",
+ " <td>zaczyna</td>\n",
+ " <td>zaczyna</td>\n",
" </tr>\n",
" <tr>\n",
" <th>67</th>\n",
" <td>SUBSTITUTION</td>\n",
- " <td>Ronda</td>\n",
- " <td>ronda</td>\n",
+ " <td>Most</td>\n",
+ " <td>most</td>\n",
" </tr>\n",
" <tr>\n",
" <th>68</th>\n",
" <td>SUBSTITUTION</td>\n",
- " <td>Żaba</td>\n",
- " <td>żaba</td>\n",
+ " <td>Siekierkowski</td>\n",
+ " <td>siekierkowski</td>\n",
" </tr>\n",
" <tr>\n",
" <th>69</th>\n",
" <td>CORRECT</td>\n",
- " <td>tak</td>\n",
- " <td>tak</td>\n",
+ " <td>tam</td>\n",
+ " <td>tam</td>\n",
" </tr>\n",
" <tr>\n",
" <th>70</th>\n",
" <td>CORRECT</td>\n",
- " <td>od</td>\n",
- " <td>od</td>\n",
+ " <td>w</td>\n",
+ " <td>w</td>\n",
" </tr>\n",
" <tr>\n",
" <th>71</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>Ronda</td>\n",
- " <td>ronda</td>\n",
+ " <td>CORRECT</td>\n",
+ " <td>stronÄ™</td>\n",
+ " <td>stronÄ™</td>\n",
" </tr>\n",
" <tr>\n",
" <th>72</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>Żaba</td>\n",
- " <td>żaba</td>\n",
+ " <td>DELETION</td>\n",
+ " <td>Gocławia</td>\n",
+ " <td></td>\n",
" </tr>\n",
" <tr>\n",
" <th>73</th>\n",
- " <td>CORRECT</td>\n",
- " <td>już</td>\n",
- " <td>już</td>\n",
+ " <td>DELETION</td>\n",
+ " <td>gdzie</td>\n",
+ " <td></td>\n",
" </tr>\n",
" <tr>\n",
" <th>74</th>\n",
- " <td>DELETION</td>\n",
- " <td>sto</td>\n",
- " <td></td>\n",
+ " <td>SUBSTITUTION</td>\n",
+ " <td>ma</td>\n",
+ " <td>wrocław</td>\n",
" </tr>\n",
" <tr>\n",
" <th>75</th>\n",
- " <td>DELETION</td>\n",
- " <td>sześćdziesiąt</td>\n",
- " <td></td>\n",
+ " <td>CORRECT</td>\n",
+ " <td>on</td>\n",
+ " <td>on</td>\n",
" </tr>\n",
" <tr>\n",
" <th>76</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>dwa</td>\n",
- " <td>162</td>\n",
+ " <td>CORRECT</td>\n",
+ " <td>przystanek</td>\n",
+ " <td>przystanek</td>\n",
" </tr>\n",
" <tr>\n",
" <th>77</th>\n",
" <td>CORRECT</td>\n",
- " <td>jest</td>\n",
- " <td>jest</td>\n",
+ " <td>pierwszy</td>\n",
+ " <td>pierwszy</td>\n",
" </tr>\n",
" <tr>\n",
" <th>78</th>\n",
@@ -880,842 +913,386 @@
" <tr>\n",
" <th>79</th>\n",
" <td>DELETION</td>\n",
- " <td>sześćdziesiąt</td>\n",
+ " <td>czterdzieści</td>\n",
" <td></td>\n",
" </tr>\n",
" <tr>\n",
" <th>80</th>\n",
" <td>SUBSTITUTION</td>\n",
- " <td>dwa</td>\n",
- " <td>162</td>\n",
+ " <td>trzy</td>\n",
+ " <td>143</td>\n",
" </tr>\n",
" <tr>\n",
" <th>81</th>\n",
" <td>CORRECT</td>\n",
- " <td>tak</td>\n",
- " <td>tak</td>\n",
+ " <td>znaczy</td>\n",
+ " <td>znaczy</td>\n",
" </tr>\n",
" <tr>\n",
" <th>82</th>\n",
" <td>CORRECT</td>\n",
- " <td>i</td>\n",
- " <td>i</td>\n",
+ " <td>tak</td>\n",
+ " <td>tak</td>\n",
" </tr>\n",
" <tr>\n",
" <th>83</th>\n",
- " <td>DELETION</td>\n",
- " <td>sto</td>\n",
- " <td></td>\n",
+ " <td>CORRECT</td>\n",
+ " <td>naprawdÄ™</td>\n",
+ " <td>naprawdÄ™</td>\n",
" </tr>\n",
" <tr>\n",
" <th>84</th>\n",
- " <td>DELETION</td>\n",
- " <td>sześćdziesiąt</td>\n",
- " <td></td>\n",
+ " <td>SUBSTITUTION</td>\n",
+ " <td>Most</td>\n",
+ " <td>most</td>\n",
" </tr>\n",
" <tr>\n",
" <th>85</th>\n",
" <td>SUBSTITUTION</td>\n",
- " <td>dwa</td>\n",
- " <td>162</td>\n",
+ " <td>Siekierkowski</td>\n",
+ " <td>siekierkowski</td>\n",
" </tr>\n",
" <tr>\n",
" <th>86</th>\n",
" <td>CORRECT</td>\n",
- " <td>tam</td>\n",
- " <td>tam</td>\n",
+ " <td>to</td>\n",
+ " <td>to</td>\n",
" </tr>\n",
" <tr>\n",
" <th>87</th>\n",
" <td>CORRECT</td>\n",
- " <td>dojadÄ™</td>\n",
- " <td>dojadÄ™</td>\n",
+ " <td>siÄ™</td>\n",
+ " <td>siÄ™</td>\n",
" </tr>\n",
" <tr>\n",
" <th>88</th>\n",
" <td>CORRECT</td>\n",
- " <td>do</td>\n",
- " <td>do</td>\n",
+ " <td>zaczyna</td>\n",
+ " <td>zaczyna</td>\n",
" </tr>\n",
" <tr>\n",
" <th>89</th>\n",
" <td>CORRECT</td>\n",
- " <td>tej</td>\n",
- " <td>tej</td>\n",
+ " <td>za</td>\n",
+ " <td>za</td>\n",
" </tr>\n",
" <tr>\n",
" <th>90</th>\n",
" <td>SUBSTITUTION</td>\n",
- " <td>ulicy</td>\n",
- " <td>uli</td>\n",
+ " <td>Siekierki</td>\n",
+ " <td>siekierki</td>\n",
" </tr>\n",
" <tr>\n",
" <th>91</th>\n",
- " <td>CORRECT</td>\n",
- " <td>tak</td>\n",
- " <td>tak</td>\n",
+ " <td>SUBSTITUTION</td>\n",
+ " <td>Sanktuarium</td>\n",
+ " <td>sanktuarium</td>\n",
" </tr>\n",
" <tr>\n",
" <th>92</th>\n",
" <td>CORRECT</td>\n",
- " <td>może</td>\n",
- " <td>może</td>\n",
+ " <td>no</td>\n",
+ " <td>no</td>\n",
" </tr>\n",
" <tr>\n",
" <th>93</th>\n",
" <td>CORRECT</td>\n",
- " <td>pani</td>\n",
- " <td>pani</td>\n",
+ " <td>właśnie</td>\n",
+ " <td>właśnie</td>\n",
" </tr>\n",
" <tr>\n",
" <th>94</th>\n",
" <td>CORRECT</td>\n",
- " <td>wysiąść</td>\n",
- " <td>wysiąść</td>\n",
+ " <td>przed</td>\n",
+ " <td>przed</td>\n",
" </tr>\n",
" <tr>\n",
" <th>95</th>\n",
- " <td>DELETION</td>\n",
- " <td>na</td>\n",
- " <td></td>\n",
+ " <td>CORRECT</td>\n",
+ " <td>tym</td>\n",
+ " <td>tym</td>\n",
" </tr>\n",
" <tr>\n",
" <th>96</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>przystanku</td>\n",
- " <td>banku</td>\n",
+ " <td>CORRECT</td>\n",
+ " <td>przed</td>\n",
+ " <td>przed</td>\n",
" </tr>\n",
" <tr>\n",
" <th>97</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>Bartycka</td>\n",
- " <td>bartycka</td>\n",
+ " <td>CORRECT</td>\n",
+ " <td>tym</td>\n",
+ " <td>tym</td>\n",
" </tr>\n",
" <tr>\n",
" <th>98</th>\n",
" <td>CORRECT</td>\n",
- " <td>albo</td>\n",
- " <td>albo</td>\n",
+ " <td>przystanek</td>\n",
+ " <td>przystanek</td>\n",
" </tr>\n",
" <tr>\n",
" <th>99</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>Sielce</td>\n",
- " <td>sielce</td>\n",
+ " <td>CORRECT</td>\n",
+ " <td>o</td>\n",
+ " <td>o</td>\n",
" </tr>\n",
" <tr>\n",
" <th>100</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>Bartycka</td>\n",
- " <td>bartycka</td>\n",
+ " <td>CORRECT</td>\n",
+ " <td>której</td>\n",
+ " <td>której</td>\n",
" </tr>\n",
" <tr>\n",
" <th>101</th>\n",
" <td>CORRECT</td>\n",
- " <td>albo</td>\n",
- " <td>albo</td>\n",
+ " <td>jest</td>\n",
+ " <td>jest</td>\n",
" </tr>\n",
" <tr>\n",
" <th>102</th>\n",
" <td>DELETION</td>\n",
- " <td>?</td>\n",
+ " <td>sto</td>\n",
" <td></td>\n",
" </tr>\n",
" <tr>\n",
" <th>103</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>Sielce</td>\n",
- " <td>sielce</td>\n",
+ " <td>DELETION</td>\n",
+ " <td>czterdzieści</td>\n",
+ " <td></td>\n",
" </tr>\n",
" <tr>\n",
" <th>104</th>\n",
" <td>SUBSTITUTION</td>\n",
- " <td>Sielce</td>\n",
- " <td>sielce</td>\n",
+ " <td>trzy</td>\n",
+ " <td>143</td>\n",
" </tr>\n",
" <tr>\n",
" <th>105</th>\n",
" <td>CORRECT</td>\n",
- " <td>tak</td>\n",
- " <td>tak</td>\n",
+ " <td>najbliższy</td>\n",
+ " <td>najbliższy</td>\n",
" </tr>\n",
" <tr>\n",
" <th>106</th>\n",
" <td>DELETION</td>\n",
- " <td>?</td>\n",
+ " <td>aha</td>\n",
" <td></td>\n",
" </tr>\n",
" <tr>\n",
" <th>107</th>\n",
- " <td>CORRECT</td>\n",
- " <td>tak</td>\n",
- " <td>tak</td>\n",
+ " <td>DELETION</td>\n",
+ " <td>czyli</td>\n",
+ " <td></td>\n",
" </tr>\n",
" <tr>\n",
" <th>108</th>\n",
- " <td>CORRECT</td>\n",
- " <td>aha</td>\n",
- " <td>aha</td>\n",
+ " <td>DELETION</td>\n",
+ " <td>to</td>\n",
+ " <td></td>\n",
" </tr>\n",
" <tr>\n",
" <th>109</th>\n",
" <td>CORRECT</td>\n",
- " <td>i</td>\n",
- " <td>i</td>\n",
+ " <td>wtedy</td>\n",
+ " <td>wtedy</td>\n",
" </tr>\n",
" <tr>\n",
" <th>110</th>\n",
" <td>CORRECT</td>\n",
- " <td>tam</td>\n",
- " <td>tam</td>\n",
+ " <td>przystanek</td>\n",
+ " <td>przystanek</td>\n",
" </tr>\n",
" <tr>\n",
" <th>111</th>\n",
- " <td>CORRECT</td>\n",
- " <td>w</td>\n",
- " <td>w</td>\n",
+ " <td>SUBSTITUTION</td>\n",
+ " <td>Małe</td>\n",
+ " <td>małe</td>\n",
" </tr>\n",
" <tr>\n",
" <th>112</th>\n",
- " <td>CORRECT</td>\n",
- " <td>pobliżu</td>\n",
- " <td>pobliżu</td>\n",
+ " <td>SUBSTITUTION</td>\n",
+ " <td>Siekierki</td>\n",
+ " <td>siekierki</td>\n",
" </tr>\n",
" <tr>\n",
" <th>113</th>\n",
" <td>CORRECT</td>\n",
- " <td>jest</td>\n",
- " <td>jest</td>\n",
+ " <td>ale</td>\n",
+ " <td>ale</td>\n",
" </tr>\n",
" <tr>\n",
" <th>114</th>\n",
" <td>CORRECT</td>\n",
- " <td>ta</td>\n",
- " <td>ta</td>\n",
+ " <td>to</td>\n",
+ " <td>to</td>\n",
" </tr>\n",
" <tr>\n",
" <th>115</th>\n",
" <td>CORRECT</td>\n",
- " <td>ulica</td>\n",
- " <td>ulica</td>\n",
+ " <td>nie</td>\n",
+ " <td>nie</td>\n",
" </tr>\n",
" <tr>\n",
" <th>116</th>\n",
- " <td>DELETION</td>\n",
- " <td>tak</td>\n",
- " <td></td>\n",
+ " <td>CORRECT</td>\n",
+ " <td>jest</td>\n",
+ " <td>jest</td>\n",
" </tr>\n",
" <tr>\n",
" <th>117</th>\n",
" <td>DELETION</td>\n",
- " <td>?</td>\n",
+ " <td>tak</td>\n",
" <td></td>\n",
" </tr>\n",
" <tr>\n",
" <th>118</th>\n",
" <td>DELETION</td>\n",
- " <td>a</td>\n",
+ " <td>tak</td>\n",
" <td></td>\n",
" </tr>\n",
" <tr>\n",
" <th>119</th>\n",
" <td>DELETION</td>\n",
- " <td>Zwierzyniecka</td>\n",
+ " <td>tak</td>\n",
" <td></td>\n",
" </tr>\n",
" <tr>\n",
" <th>120</th>\n",
" <td>DELETION</td>\n",
- " <td>wysoki</td>\n",
+ " <td>tak</td>\n",
" <td></td>\n",
" </tr>\n",
" <tr>\n",
" <th>121</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>numer</td>\n",
- " <td>zwierzyniecka</td>\n",
+ " <td>DELETION</td>\n",
+ " <td>na</td>\n",
+ " <td></td>\n",
" </tr>\n",
" <tr>\n",
" <th>122</th>\n",
- " <td>CORRECT</td>\n",
- " <td>ma</td>\n",
- " <td>ma</td>\n",
+ " <td>DELETION</td>\n",
+ " <td>wysokości</td>\n",
+ " <td></td>\n",
" </tr>\n",
" <tr>\n",
" <th>123</th>\n",
- " <td>CORRECT</td>\n",
- " <td>pani</td>\n",
- " <td>pani</td>\n",
+ " <td>SUBSTITUTION</td>\n",
+ " <td>Panoramy</td>\n",
+ " <td>dokonać</td>\n",
" </tr>\n",
" <tr>\n",
" <th>124</th>\n",
" <td>SUBSTITUTION</td>\n",
- " <td>?</td>\n",
- " <td>zwierzyniecka</td>\n",
+ " <td>aha</td>\n",
+ " <td>panoramy</td>\n",
" </tr>\n",
" <tr>\n",
" <th>125</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>Zwierzyniecka</td>\n",
- " <td>telefonem</td>\n",
+ " <td>CORRECT</td>\n",
+ " <td>dobrze</td>\n",
+ " <td>dobrze</td>\n",
" </tr>\n",
" <tr>\n",
" <th>126</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>zaraz</td>\n",
- " <td>dzikie</td>\n",
+ " <td>CORRECT</td>\n",
+ " <td>najbliższy</td>\n",
+ " <td>najbliższy</td>\n",
" </tr>\n",
" <tr>\n",
" <th>127</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>momencik</td>\n",
- " <td>który</td>\n",
+ " <td>CORRECT</td>\n",
+ " <td>już</td>\n",
+ " <td>już</td>\n",
" </tr>\n",
" <tr>\n",
" <th>128</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>osiem</td>\n",
- " <td>8</td>\n",
+ " <td>CORRECT</td>\n",
+ " <td>chwileczkÄ™</td>\n",
+ " <td>chwileczkÄ™</td>\n",
" </tr>\n",
" <tr>\n",
" <th>129</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>A</td>\n",
- " <td>a</td>\n",
+ " <td>CORRECT</td>\n",
+ " <td>czternasta</td>\n",
+ " <td>czternasta</td>\n",
" </tr>\n",
" <tr>\n",
" <th>130</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>Zwierzyniecka</td>\n",
- " <td>zwierzyniecka</td>\n",
+ " <td>DELETION</td>\n",
+ " <td>czterdzieści</td>\n",
+ " <td></td>\n",
" </tr>\n",
" <tr>\n",
" <th>131</th>\n",
- " <td>CORRECT</td>\n",
- " <td>to</td>\n",
- " <td>to</td>\n",
+ " <td>SUBSTITUTION</td>\n",
+ " <td>sześć</td>\n",
+ " <td>46</td>\n",
" </tr>\n",
" <tr>\n",
" <th>132</th>\n",
" <td>CORRECT</td>\n",
- " <td>to</td>\n",
- " <td>to</td>\n",
+ " <td>piętnasta</td>\n",
+ " <td>piętnasta</td>\n",
" </tr>\n",
" <tr>\n",
" <th>133</th>\n",
- " <td>CORRECT</td>\n",
- " <td>przy</td>\n",
- " <td>przy</td>\n",
+ " <td>SUBSTITUTION</td>\n",
+ " <td>zero</td>\n",
+ " <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>134</th>\n",
" <td>SUBSTITUTION</td>\n",
- " <td>Sielce</td>\n",
- " <td>sielce</td>\n",
+ " <td>jeden</td>\n",
+ " <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>135</th>\n",
" <td>CORRECT</td>\n",
- " <td>trza</td>\n",
- " <td>trza</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>136</th>\n",
- " <td>CORRECT</td>\n",
- " <td>wysiąść</td>\n",
- " <td>wysiąść</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>137</th>\n",
- " <td>CORRECT</td>\n",
- " <td>przy</td>\n",
- " <td>przy</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>138</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>Sielce</td>\n",
- " <td>sielce</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>139</th>\n",
- " <td>CORRECT</td>\n",
- " <td>tak</td>\n",
- " <td>tak</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>140</th>\n",
- " <td>DELETION</td>\n",
- " <td>?</td>\n",
- " <td></td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>141</th>\n",
- " <td>CORRECT</td>\n",
- " <td>tak</td>\n",
- " <td>tak</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>142</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>przystanek</td>\n",
- " <td>stanek</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>143</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>Sielce</td>\n",
- " <td>sielce</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>144</th>\n",
- " <td>CORRECT</td>\n",
" <td>aha</td>\n",
" <td>aha</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>145</th>\n",
+ " <th>136</th>\n",
" <td>DELETION</td>\n",
- " <td>tak</td>\n",
- " <td></td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>146</th>\n",
- " <td>CORRECT</td>\n",
- " <td>no</td>\n",
" <td>no</td>\n",
+ " <td></td>\n",
" </tr>\n",
" <tr>\n",
- " <th>147</th>\n",
+ " <th>137</th>\n",
" <td>CORRECT</td>\n",
" <td>dobrze</td>\n",
" <td>dobrze</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>148</th>\n",
+ " <th>138</th>\n",
" <td>CORRECT</td>\n",
- " <td>a</td>\n",
- " <td>a</td>\n",
+ " <td>dziękuję</td>\n",
+ " <td>dziękuję</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>149</th>\n",
+ " <th>139</th>\n",
" <td>DELETION</td>\n",
- " <td>Sielce</td>\n",
+ " <td>do</td>\n",
" <td></td>\n",
" </tr>\n",
" <tr>\n",
- " <th>150</th>\n",
+ " <th>140</th>\n",
" <td>DELETION</td>\n",
- " <td>to</td>\n",
+ " <td>widzenia</td>\n",
" <td></td>\n",
" </tr>\n",
" <tr>\n",
- " <th>151</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>znaczy</td>\n",
- " <td>sielce</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>152</th>\n",
+ " <th>141</th>\n",
" <td>CORRECT</td>\n",
- " <td>jaka</td>\n",
- " <td>jaka</td>\n",
+ " <td>do</td>\n",
+ " <td>do</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>153</th>\n",
+ " <th>142</th>\n",
" <td>CORRECT</td>\n",
- " <td>to</td>\n",
- " <td>to</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>154</th>\n",
- " <td>CORRECT</td>\n",
- " <td>już</td>\n",
- " <td>już</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>155</th>\n",
- " <td>CORRECT</td>\n",
- " <td>jest</td>\n",
- " <td>jest</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>156</th>\n",
- " <td>CORRECT</td>\n",
- " <td>dzielnica</td>\n",
- " <td>dzielnica</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>157</th>\n",
- " <td>CORRECT</td>\n",
- " <td>to</td>\n",
- " <td>to</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>158</th>\n",
- " <td>CORRECT</td>\n",
- " <td>ta</td>\n",
- " <td>ta</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>159</th>\n",
- " <td>CORRECT</td>\n",
- " <td>jest</td>\n",
- " <td>jest</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>160</th>\n",
- " <td>CORRECT</td>\n",
- " <td>przy</td>\n",
- " <td>przy</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>161</th>\n",
- " <td>CORRECT</td>\n",
- " <td>ulica</td>\n",
- " <td>ulica</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>162</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>Gagarina</td>\n",
- " <td>gagarina</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>163</th>\n",
- " <td>CORRECT</td>\n",
- " <td>a</td>\n",
- " <td>a</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>164</th>\n",
- " <td>CORRECT</td>\n",
- " <td>przy</td>\n",
- " <td>przy</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>165</th>\n",
- " <td>CORRECT</td>\n",
- " <td>ulicy</td>\n",
- " <td>ulicy</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>166</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>Gagarina</td>\n",
- " <td>gagarina</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>167</th>\n",
- " <td>CORRECT</td>\n",
- " <td>czyli</td>\n",
- " <td>czyli</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>168</th>\n",
- " <td>CORRECT</td>\n",
- " <td>to</td>\n",
- " <td>to</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>169</th>\n",
- " <td>CORRECT</td>\n",
- " <td>jest</td>\n",
- " <td>jest</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>170</th>\n",
- " <td>CORRECT</td>\n",
- " <td>tam</td>\n",
- " <td>tam</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>171</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>Mokotów</td>\n",
- " <td>mokotów</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>172</th>\n",
- " <td>CORRECT</td>\n",
- " <td>po</td>\n",
- " <td>po</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>173</th>\n",
- " <td>CORRECT</td>\n",
- " <td>prostu</td>\n",
- " <td>prostu</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>174</th>\n",
- " <td>CORRECT</td>\n",
- " <td>tak</td>\n",
- " <td>tak</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>175</th>\n",
- " <td>DELETION</td>\n",
- " <td>?</td>\n",
- " <td></td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>176</th>\n",
- " <td>CORRECT</td>\n",
- " <td>tak</td>\n",
- " <td>tak</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>177</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>Siekierki</td>\n",
- " <td>siekierki</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>178</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>Mokotów</td>\n",
- " <td>mokot</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>179</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>a</td>\n",
- " <td>siekierki</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>180</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>Siekierki</td>\n",
- " <td>mokot</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>181</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>Mokotów</td>\n",
- " <td>ów</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>182</th>\n",
- " <td>CORRECT</td>\n",
- " <td>i</td>\n",
- " <td>i</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>183</th>\n",
- " <td>CORRECT</td>\n",
- " <td>tam</td>\n",
- " <td>tam</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>184</th>\n",
- " <td>CORRECT</td>\n",
- " <td>jak</td>\n",
- " <td>jak</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>185</th>\n",
- " <td>CORRECT</td>\n",
- " <td>pani</td>\n",
- " <td>pani</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>186</th>\n",
- " <td>CORRECT</td>\n",
- " <td>wysiÄ…dzie</td>\n",
- " <td>wysiÄ…dzie</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>187</th>\n",
- " <td>CORRECT</td>\n",
- " <td>to</td>\n",
- " <td>to</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>188</th>\n",
- " <td>CORRECT</td>\n",
- " <td>trza</td>\n",
- " <td>trza</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>189</th>\n",
- " <td>CORRECT</td>\n",
- " <td>wejść</td>\n",
- " <td>wejść</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>190</th>\n",
- " <td>DELETION</td>\n",
- " <td>w</td>\n",
- " <td></td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>191</th>\n",
- " <td>DELETION</td>\n",
- " <td>lewo</td>\n",
- " <td></td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>192</th>\n",
- " <td>DELETION</td>\n",
- " <td>w</td>\n",
- " <td></td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>193</th>\n",
- " <td>DELETION</td>\n",
- " <td>ulicÄ™</td>\n",
- " <td></td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>194</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>Nehru</td>\n",
- " <td>scenerii</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>195</th>\n",
- " <td>CORRECT</td>\n",
- " <td>i</td>\n",
- " <td>i</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>196</th>\n",
- " <td>CORRECT</td>\n",
- " <td>od</td>\n",
- " <td>od</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>197</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>Nehru</td>\n",
- " <td>nehru</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>198</th>\n",
- " <td>CORRECT</td>\n",
- " <td>odchodzi</td>\n",
- " <td>odchodzi</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>199</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>Zwierzyniecka</td>\n",
- " <td>zwierzyniecka</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>200</th>\n",
- " <td>CORRECT</td>\n",
- " <td>w</td>\n",
- " <td>w</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>201</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>lewo</td>\n",
- " <td>le</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>202</th>\n",
- " <td>CORRECT</td>\n",
- " <td>w</td>\n",
- " <td>w</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>203</th>\n",
- " <td>CORRECT</td>\n",
- " <td>lewo</td>\n",
- " <td>lewo</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>204</th>\n",
- " <td>CORRECT</td>\n",
- " <td>i</td>\n",
- " <td>i</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>205</th>\n",
- " <td>CORRECT</td>\n",
- " <td>ulica</td>\n",
- " <td>ulica</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>206</th>\n",
- " <td>DELETION</td>\n",
- " <td>Nehru</td>\n",
- " <td></td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>207</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>?</td>\n",
- " <td>nehru</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>208</th>\n",
- " <td>CORRECT</td>\n",
- " <td>tak</td>\n",
- " <td>tak</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>209</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>Nehru</td>\n",
- " <td>nehru</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>210</th>\n",
- " <td>CORRECT</td>\n",
- " <td>dobrze</td>\n",
- " <td>dobrze</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>211</th>\n",
- " <td>CORRECT</td>\n",
- " <td>dziękuję</td>\n",
- " <td>dziękuję</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>212</th>\n",
- " <td>CORRECT</td>\n",
- " <td>panu</td>\n",
- " <td>panu</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>213</th>\n",
- " <td>CORRECT</td>\n",
- " <td>bardzo</td>\n",
- " <td>bardzo</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>214</th>\n",
- " <td>DELETION</td>\n",
- " <td>proszÄ™</td>\n",
- " <td></td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>215</th>\n",
- " <td>CORRECT</td>\n",
- " <td>do</td>\n",
- " <td>do</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>216</th>\n",
- " <td>CORRECT</td>\n",
- " <td>widzenia</td>\n",
- " <td>widzenia</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>217</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>do</td>\n",
- " <td>to</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>218</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>widzenia</td>\n",
- " <td>wszystko</td>\n",
+ " <td>widzenia</td>\n",
+ " <td>widzenia</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
@@ -1731,217 +1308,141 @@
"5 CORRECT proszÄ™ proszÄ™\n",
"6 CORRECT pana pana\n",
"7 CORRECT ja ja\n",
- "8 CORRECT chciałam chciałam\n",
- "9 CORRECT siÄ™ siÄ™\n",
- "10 CORRECT dowiedzieć dowiedzieć\n",
- "11 CORRECT bo bo\n",
- "12 CORRECT nie nie\n",
- "13 CORRECT bardzo bardzo\n",
- "14 CORRECT wiem wiem\n",
- "15 CORRECT gdzie gdzie\n",
- "16 CORRECT znajduje znajduje\n",
- "17 CORRECT siÄ™ siÄ™\n",
- "18 CORRECT ulica ulica\n",
- "19 SUBSTITUTION Zwierzyniecka zwierzyniecka\n",
- "20 CORRECT i i\n",
- "21 CORRECT jak jak\n",
- "22 CORRECT dojechać dojechać\n",
- "23 CORRECT z z\n",
- "24 DELETION Bródna \n",
- "25 DELETION na \n",
- "26 DELETION przykład \n",
- "27 SUBSTITUTION ? bródna\n",
- "28 CORRECT na na\n",
- "29 SUBSTITUTION ZwierzynieckÄ… zwierzynieckÄ…\n",
- "30 CORRECT na na\n",
- "31 SUBSTITUTION ZwierzynieckÄ… zwierzynieckÄ…\n",
- "32 SUBSTITUTION a ja\n",
- "33 CORRECT z z\n",
- "34 SUBSTITUTION Bródna bródna\n",
- "35 CORRECT z z\n",
- "36 CORRECT którego którego\n",
- "37 CORRECT miejsca miejsca\n",
- "38 DELETION ? \n",
- "39 CORRECT z z\n",
- "40 SUBSTITUTION Bródna bródna\n",
- "41 CORRECT to to\n",
- "42 CORRECT jest jest\n",
- "43 CORRECT ulica ulica\n",
- "44 SUBSTITUTION Wyszogrodzka wyszogrodzka\n",
- "45 CORRECT tu tu\n",
- "46 CORRECT przy przy\n",
- "47 SUBSTITUTION Rembielińskiej rembielińskiej\n",
- "48 CORRECT czyli czyli\n",
- "49 CORRECT przy przy\n",
- "50 CORRECT tramwajach tramwajach\n",
- "51 DELETION tak \n",
- "52 DELETION ? \n",
- "53 CORRECT przy przy\n",
- "54 CORRECT tramwajach tramwajach\n",
- "55 CORRECT tak tak\n",
- "56 CORRECT może może\n",
- "57 DELETION pani \n",
- "58 DELETION poczeka \n",
- "59 CORRECT sprawdzÄ™ sprawdzÄ™\n",
- "60 CORRECT dobrze dobrze\n",
- "61 CORRECT dobrze dobrze\n",
- "62 DELETION pani \n",
- "63 DELETION sobie \n",
- "64 CORRECT podjedzie podjedzie\n",
- "65 CORRECT tramwajem tramwajem\n",
- "66 CORRECT do do\n",
- "67 SUBSTITUTION Ronda ronda\n",
- "68 SUBSTITUTION Żaba żaba\n",
- "69 CORRECT tak tak\n",
- "70 CORRECT od od\n",
- "71 SUBSTITUTION Ronda ronda\n",
- "72 SUBSTITUTION Żaba żaba\n",
- "73 CORRECT już już\n",
- "74 DELETION sto \n",
- "75 DELETION sześćdziesiąt \n",
- "76 SUBSTITUTION dwa 162\n",
- "77 CORRECT jest jest\n",
+ "8 CORRECT mam mam\n",
+ "9 INSERTION pytanie\n",
+ "10 CORRECT o o\n",
+ "11 CORRECT której której\n",
+ "12 CORRECT będzie będzie\n",
+ "13 DELETION sto \n",
+ "14 DELETION czterdzieści \n",
+ "15 SUBSTITUTION trzy 143\n",
+ "16 CORRECT będzie będzie\n",
+ "17 CORRECT najbliższy najbliższy\n",
+ "18 CORRECT z z\n",
+ "19 INSERTION alei\n",
+ "20 SUBSTITUTION Alei witosa\n",
+ "21 SUBSTITUTION Alei alei\n",
+ "22 SUBSTITUTION Witosa witosa\n",
+ "23 CORRECT w w\n",
+ "24 CORRECT stronÄ™ stronÄ™\n",
+ "25 DELETION Gocławia \n",
+ "26 DELETION z \n",
+ "27 SUBSTITUTION tego gocławia\n",
+ "28 CORRECT przystanku przystanku\n",
+ "29 SUBSTITUTION vis-a-vis widzowi\n",
+ "30 SUBSTITUTION ZUSu zusu\n",
+ "31 CORRECT tak tak\n",
+ "32 DELETION ? \n",
+ "33 CORRECT no no\n",
+ "34 CORRECT nie nie\n",
+ "35 CORRECT nie nie\n",
+ "36 CORRECT tam tam\n",
+ "37 SUBSTITUTION vis-a-vis widzowi\n",
+ "38 SUBSTITUTION Panoramy panoramy\n",
+ "39 CORRECT przez przez\n",
+ "40 SUBSTITUTION Siekierkowski siekierkowski\n",
+ "41 CORRECT tam tam\n",
+ "42 CORRECT w w\n",
+ "43 CORRECT stronÄ™ stronÄ™\n",
+ "44 SUBSTITUTION Gocławia gocławia\n",
+ "45 CORRECT ale ale\n",
+ "46 CORRECT to to\n",
+ "47 CORRECT nie nie\n",
+ "48 CORRECT z z\n",
+ "49 CORRECT tego tego\n",
+ "50 CORRECT przystanku przystanku\n",
+ "51 DELETION Aleja \n",
+ "52 SUBSTITUTION Witosa aleja\n",
+ "53 SUBSTITUTION ? witosa\n",
+ "54 CORRECT no no\n",
+ "55 CORRECT to to\n",
+ "56 CORRECT jest jest\n",
+ "57 CORRECT czy czy\n",
+ "58 SUBSTITUTION Bartoszka bartoszka\n",
+ "59 CORRECT na na\n",
+ "60 CORRECT żądanie żądanie\n",
+ "61 CORRECT wie wie\n",
+ "62 CORRECT pan pan\n",
+ "63 CORRECT gdzie gdzie\n",
+ "64 CORRECT jest jest\n",
+ "65 CORRECT siÄ™ siÄ™\n",
+ "66 CORRECT zaczyna zaczyna\n",
+ "67 SUBSTITUTION Most most\n",
+ "68 SUBSTITUTION Siekierkowski siekierkowski\n",
+ "69 CORRECT tam tam\n",
+ "70 CORRECT w w\n",
+ "71 CORRECT stronÄ™ stronÄ™\n",
+ "72 DELETION Gocławia \n",
+ "73 DELETION gdzie \n",
+ "74 SUBSTITUTION ma wrocław\n",
+ "75 CORRECT on on\n",
+ "76 CORRECT przystanek przystanek\n",
+ "77 CORRECT pierwszy pierwszy\n",
"78 DELETION sto \n",
- "79 DELETION sześćdziesiąt \n",
- "80 SUBSTITUTION dwa 162\n",
- "81 CORRECT tak tak\n",
- "82 CORRECT i i\n",
- "83 DELETION sto \n",
- "84 DELETION sześćdziesiąt \n",
- "85 SUBSTITUTION dwa 162\n",
- "86 CORRECT tam tam\n",
- "87 CORRECT dojadÄ™ dojadÄ™\n",
- "88 CORRECT do do\n",
- "89 CORRECT tej tej\n",
- "90 SUBSTITUTION ulicy uli\n",
- "91 CORRECT tak tak\n",
- "92 CORRECT może może\n",
- "93 CORRECT pani pani\n",
- "94 CORRECT wysiąść wysiąść\n",
- "95 DELETION na \n",
- "96 SUBSTITUTION przystanku banku\n",
- "97 SUBSTITUTION Bartycka bartycka\n",
- "98 CORRECT albo albo\n",
- "99 SUBSTITUTION Sielce sielce\n",
- "100 SUBSTITUTION Bartycka bartycka\n",
- "101 CORRECT albo albo\n",
- "102 DELETION ? \n",
- "103 SUBSTITUTION Sielce sielce\n",
- "104 SUBSTITUTION Sielce sielce\n",
- "105 CORRECT tak tak\n",
- "106 DELETION ? \n",
- "107 CORRECT tak tak\n",
- "108 CORRECT aha aha\n",
- "109 CORRECT i i\n",
- "110 CORRECT tam tam\n",
- "111 CORRECT w w\n",
- "112 CORRECT pobliżu pobliżu\n",
- "113 CORRECT jest jest\n",
- "114 CORRECT ta ta\n",
- "115 CORRECT ulica ulica\n",
- "116 DELETION tak \n",
- "117 DELETION ? \n",
- "118 DELETION a \n",
- "119 DELETION Zwierzyniecka \n",
- "120 DELETION wysoki \n",
- "121 SUBSTITUTION numer zwierzyniecka\n",
- "122 CORRECT ma ma\n",
- "123 CORRECT pani pani\n",
- "124 SUBSTITUTION ? zwierzyniecka\n",
- "125 SUBSTITUTION Zwierzyniecka telefonem\n",
- "126 SUBSTITUTION zaraz dzikie\n",
- "127 SUBSTITUTION momencik który\n",
- "128 SUBSTITUTION osiem 8\n",
- "129 SUBSTITUTION A a\n",
- "130 SUBSTITUTION Zwierzyniecka zwierzyniecka\n",
- "131 CORRECT to to\n",
- "132 CORRECT to to\n",
- "133 CORRECT przy przy\n",
- "134 SUBSTITUTION Sielce sielce\n",
- "135 CORRECT trza trza\n",
- "136 CORRECT wysiąść wysiąść\n",
- "137 CORRECT przy przy\n",
- "138 SUBSTITUTION Sielce sielce\n",
- "139 CORRECT tak tak\n",
- "140 DELETION ? \n",
- "141 CORRECT tak tak\n",
- "142 SUBSTITUTION przystanek stanek\n",
- "143 SUBSTITUTION Sielce sielce\n",
- "144 CORRECT aha aha\n",
- "145 DELETION tak \n",
- "146 CORRECT no no\n",
- "147 CORRECT dobrze dobrze\n",
- "148 CORRECT a a\n",
- "149 DELETION Sielce \n",
- "150 DELETION to \n",
- "151 SUBSTITUTION znaczy sielce\n",
- "152 CORRECT jaka jaka\n",
- "153 CORRECT to to\n",
- "154 CORRECT już już\n",
- "155 CORRECT jest jest\n",
- "156 CORRECT dzielnica dzielnica\n",
- "157 CORRECT to to\n",
- "158 CORRECT ta ta\n",
- "159 CORRECT jest jest\n",
- "160 CORRECT przy przy\n",
- "161 CORRECT ulica ulica\n",
- "162 SUBSTITUTION Gagarina gagarina\n",
- "163 CORRECT a a\n",
- "164 CORRECT przy przy\n",
- "165 CORRECT ulicy ulicy\n",
- "166 SUBSTITUTION Gagarina gagarina\n",
- "167 CORRECT czyli czyli\n",
- "168 CORRECT to to\n",
- "169 CORRECT jest jest\n",
- "170 CORRECT tam tam\n",
- "171 SUBSTITUTION Mokotów mokotów\n",
- "172 CORRECT po po\n",
- "173 CORRECT prostu prostu\n",
- "174 CORRECT tak tak\n",
- "175 DELETION ? \n",
- "176 CORRECT tak tak\n",
- "177 SUBSTITUTION Siekierki siekierki\n",
- "178 SUBSTITUTION Mokotów mokot\n",
- "179 SUBSTITUTION a siekierki\n",
- "180 SUBSTITUTION Siekierki mokot\n",
- "181 SUBSTITUTION Mokotów ów\n",
- "182 CORRECT i i\n",
- "183 CORRECT tam tam\n",
- "184 CORRECT jak jak\n",
- "185 CORRECT pani pani\n",
- "186 CORRECT wysiÄ…dzie wysiÄ…dzie\n",
- "187 CORRECT to to\n",
- "188 CORRECT trza trza\n",
- "189 CORRECT wejść wejść\n",
- "190 DELETION w \n",
- "191 DELETION lewo \n",
- "192 DELETION w \n",
- "193 DELETION ulicÄ™ \n",
- "194 SUBSTITUTION Nehru scenerii\n",
- "195 CORRECT i i\n",
- "196 CORRECT od od\n",
- "197 SUBSTITUTION Nehru nehru\n",
- "198 CORRECT odchodzi odchodzi\n",
- "199 SUBSTITUTION Zwierzyniecka zwierzyniecka\n",
- "200 CORRECT w w\n",
- "201 SUBSTITUTION lewo le\n",
- "202 CORRECT w w\n",
- "203 CORRECT lewo lewo\n",
- "204 CORRECT i i\n",
- "205 CORRECT ulica ulica\n",
- "206 DELETION Nehru \n",
- "207 SUBSTITUTION ? nehru\n",
- "208 CORRECT tak tak\n",
- "209 SUBSTITUTION Nehru nehru\n",
- "210 CORRECT dobrze dobrze\n",
- "211 CORRECT dziękuję dziękuję\n",
- "212 CORRECT panu panu\n",
- "213 CORRECT bardzo bardzo\n",
- "214 DELETION proszÄ™ \n",
- "215 CORRECT do do\n",
- "216 CORRECT widzenia widzenia\n",
- "217 SUBSTITUTION do to\n",
- "218 SUBSTITUTION widzenia wszystko"
+ "79 DELETION czterdzieści \n",
+ "80 SUBSTITUTION trzy 143\n",
+ "81 CORRECT znaczy znaczy\n",
+ "82 CORRECT tak tak\n",
+ "83 CORRECT naprawdÄ™ naprawdÄ™\n",
+ "84 SUBSTITUTION Most most\n",
+ "85 SUBSTITUTION Siekierkowski siekierkowski\n",
+ "86 CORRECT to to\n",
+ "87 CORRECT siÄ™ siÄ™\n",
+ "88 CORRECT zaczyna zaczyna\n",
+ "89 CORRECT za za\n",
+ "90 SUBSTITUTION Siekierki siekierki\n",
+ "91 SUBSTITUTION Sanktuarium sanktuarium\n",
+ "92 CORRECT no no\n",
+ "93 CORRECT właśnie właśnie\n",
+ "94 CORRECT przed przed\n",
+ "95 CORRECT tym tym\n",
+ "96 CORRECT przed przed\n",
+ "97 CORRECT tym tym\n",
+ "98 CORRECT przystanek przystanek\n",
+ "99 CORRECT o o\n",
+ "100 CORRECT której której\n",
+ "101 CORRECT jest jest\n",
+ "102 DELETION sto \n",
+ "103 DELETION czterdzieści \n",
+ "104 SUBSTITUTION trzy 143\n",
+ "105 CORRECT najbliższy najbliższy\n",
+ "106 DELETION aha \n",
+ "107 DELETION czyli \n",
+ "108 DELETION to \n",
+ "109 CORRECT wtedy wtedy\n",
+ "110 CORRECT przystanek przystanek\n",
+ "111 SUBSTITUTION Małe małe\n",
+ "112 SUBSTITUTION Siekierki siekierki\n",
+ "113 CORRECT ale ale\n",
+ "114 CORRECT to to\n",
+ "115 CORRECT nie nie\n",
+ "116 CORRECT jest jest\n",
+ "117 DELETION tak \n",
+ "118 DELETION tak \n",
+ "119 DELETION tak \n",
+ "120 DELETION tak \n",
+ "121 DELETION na \n",
+ "122 DELETION wysokości \n",
+ "123 SUBSTITUTION Panoramy dokonać\n",
+ "124 SUBSTITUTION aha panoramy\n",
+ "125 CORRECT dobrze dobrze\n",
+ "126 CORRECT najbliższy najbliższy\n",
+ "127 CORRECT już już\n",
+ "128 CORRECT chwileczkÄ™ chwileczkÄ™\n",
+ "129 CORRECT czternasta czternasta\n",
+ "130 DELETION czterdzieści \n",
+ "131 SUBSTITUTION sześć 46\n",
+ "132 CORRECT piętnasta piętnasta\n",
+ "133 SUBSTITUTION zero 0\n",
+ "134 SUBSTITUTION jeden 1\n",
+ "135 CORRECT aha aha\n",
+ "136 DELETION no \n",
+ "137 CORRECT dobrze dobrze\n",
+ "138 CORRECT dziękuję dziękuję\n",
+ "139 DELETION do \n",
+ "140 DELETION widzenia \n",
+ "141 CORRECT do do\n",
+ "142 CORRECT widzenia widzenia"
]
},
"metadata": {},
@@ -2051,604 +1552,620 @@
" <th>8</th>\n",
" <td>CORRECT</td>\n",
" <td>VERB</td>\n",
- " <td>chciałam</td>\n",
+ " <td>mam</td>\n",
" <td>VERB</td>\n",
- " <td>chciałam</td>\n",
+ " <td>mam</td>\n",
" </tr>\n",
" <tr>\n",
" <th>9</th>\n",
- " <td>CORRECT</td>\n",
- " <td>PRON</td>\n",
- " <td>siÄ™</td>\n",
- " <td>PRON</td>\n",
- " <td>siÄ™</td>\n",
+ " <td>INSERTION</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>NOUN</td>\n",
+ " <td>pytanie</td>\n",
" </tr>\n",
" <tr>\n",
" <th>10</th>\n",
" <td>CORRECT</td>\n",
- " <td>VERB</td>\n",
- " <td>dowiedzieć</td>\n",
- " <td>VERB</td>\n",
- " <td>dowiedzieć</td>\n",
+ " <td>ADP</td>\n",
+ " <td>o</td>\n",
+ " <td>ADP</td>\n",
+ " <td>o</td>\n",
" </tr>\n",
" <tr>\n",
" <th>11</th>\n",
" <td>CORRECT</td>\n",
- " <td>SCONJ</td>\n",
- " <td>bo</td>\n",
- " <td>SCONJ</td>\n",
- " <td>bo</td>\n",
+ " <td>DET</td>\n",
+ " <td>której</td>\n",
+ " <td>DET</td>\n",
+ " <td>której</td>\n",
" </tr>\n",
" <tr>\n",
" <th>12</th>\n",
" <td>CORRECT</td>\n",
- " <td>PART</td>\n",
- " <td>nie</td>\n",
- " <td>PART</td>\n",
- " <td>nie</td>\n",
+ " <td>VERB</td>\n",
+ " <td>będzie</td>\n",
+ " <td>VERB</td>\n",
+ " <td>będzie</td>\n",
" </tr>\n",
" <tr>\n",
" <th>13</th>\n",
- " <td>CORRECT</td>\n",
- " <td>ADV</td>\n",
- " <td>bardzo</td>\n",
- " <td>ADV</td>\n",
- " <td>bardzo</td>\n",
+ " <td>DELETION</td>\n",
+ " <td>NUM</td>\n",
+ " <td>sto</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
" </tr>\n",
" <tr>\n",
" <th>14</th>\n",
- " <td>CORRECT</td>\n",
- " <td>VERB</td>\n",
- " <td>wiem</td>\n",
- " <td>VERB</td>\n",
- " <td>wiem</td>\n",
+ " <td>DELETION</td>\n",
+ " <td>ADJ</td>\n",
+ " <td>czterdzieści</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
" </tr>\n",
" <tr>\n",
" <th>15</th>\n",
- " <td>CORRECT</td>\n",
- " <td>ADV</td>\n",
- " <td>gdzie</td>\n",
- " <td>ADV</td>\n",
- " <td>gdzie</td>\n",
+ " <td>SUBSTITUTION</td>\n",
+ " <td>NUM</td>\n",
+ " <td>trzy</td>\n",
+ " <td>X</td>\n",
+ " <td>143</td>\n",
" </tr>\n",
" <tr>\n",
" <th>16</th>\n",
" <td>CORRECT</td>\n",
- " <td>VERB</td>\n",
- " <td>znajduje</td>\n",
- " <td>VERB</td>\n",
- " <td>znajduje</td>\n",
+ " <td>AUX</td>\n",
+ " <td>będzie</td>\n",
+ " <td>AUX</td>\n",
+ " <td>będzie</td>\n",
" </tr>\n",
" <tr>\n",
" <th>17</th>\n",
" <td>CORRECT</td>\n",
- " <td>PRON</td>\n",
- " <td>siÄ™</td>\n",
- " <td>PRON</td>\n",
- " <td>siÄ™</td>\n",
+ " <td>ADJ</td>\n",
+ " <td>najbliższy</td>\n",
+ " <td>ADJ</td>\n",
+ " <td>najbliższy</td>\n",
" </tr>\n",
" <tr>\n",
" <th>18</th>\n",
" <td>CORRECT</td>\n",
- " <td>NOUN</td>\n",
- " <td>ulica</td>\n",
- " <td>NOUN</td>\n",
- " <td>ulica</td>\n",
+ " <td>ADP</td>\n",
+ " <td>z</td>\n",
+ " <td>ADP</td>\n",
+ " <td>z</td>\n",
" </tr>\n",
" <tr>\n",
" <th>19</th>\n",
" <td>CORRECT</td>\n",
- " <td>ADJ</td>\n",
- " <td>Zwierzyniecka</td>\n",
- " <td>ADJ</td>\n",
- " <td>zwierzyniecka</td>\n",
+ " <td>NOUN</td>\n",
+ " <td>Alei</td>\n",
+ " <td>NOUN</td>\n",
+ " <td>alei</td>\n",
" </tr>\n",
" <tr>\n",
" <th>20</th>\n",
" <td>CORRECT</td>\n",
- " <td>CCONJ</td>\n",
- " <td>i</td>\n",
- " <td>CCONJ</td>\n",
- " <td>i</td>\n",
+ " <td>NOUN</td>\n",
+ " <td>Alei</td>\n",
+ " <td>NOUN</td>\n",
+ " <td>witosa</td>\n",
" </tr>\n",
" <tr>\n",
" <th>21</th>\n",
- " <td>CORRECT</td>\n",
- " <td>ADV</td>\n",
- " <td>jak</td>\n",
- " <td>ADV</td>\n",
- " <td>jak</td>\n",
+ " <td>DELETION</td>\n",
+ " <td>PROPN</td>\n",
+ " <td>Witosa</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
" </tr>\n",
" <tr>\n",
" <th>22</th>\n",
- " <td>CORRECT</td>\n",
- " <td>VERB</td>\n",
- " <td>dojechać</td>\n",
- " <td>VERB</td>\n",
- " <td>dojechać</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>23</th>\n",
" <td>DELETION</td>\n",
" <td>ADP</td>\n",
- " <td>z</td>\n",
+ " <td>w</td>\n",
" <td></td>\n",
" <td></td>\n",
" </tr>\n",
" <tr>\n",
+ " <th>23</th>\n",
+ " <td>CORRECT</td>\n",
+ " <td>NOUN</td>\n",
+ " <td>stronÄ™</td>\n",
+ " <td>NOUN</td>\n",
+ " <td>alei</td>\n",
+ " </tr>\n",
+ " <tr>\n",
" <th>24</th>\n",
- " <td>DELETION</td>\n",
+ " <td>SUBSTITUTION</td>\n",
" <td>PROPN</td>\n",
- " <td>Bródna</td>\n",
- " <td></td>\n",
- " <td></td>\n",
+ " <td>Gocławia</td>\n",
+ " <td>NOUN</td>\n",
+ " <td>witosa</td>\n",
" </tr>\n",
" <tr>\n",
" <th>25</th>\n",
" <td>CORRECT</td>\n",
" <td>ADP</td>\n",
- " <td>na</td>\n",
- " <td>ADP</td>\n",
" <td>z</td>\n",
+ " <td>ADP</td>\n",
+ " <td>w</td>\n",
" </tr>\n",
" <tr>\n",
" <th>26</th>\n",
- " <td>CORRECT</td>\n",
- " <td>NOUN</td>\n",
- " <td>przykład</td>\n",
- " <td>NOUN</td>\n",
- " <td>bródna</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>27</th>\n",
" <td>DELETION</td>\n",
- " <td>PUNCT</td>\n",
- " <td>?</td>\n",
+ " <td>DET</td>\n",
+ " <td>tego</td>\n",
" <td></td>\n",
" <td></td>\n",
" </tr>\n",
" <tr>\n",
+ " <th>27</th>\n",
+ " <td>CORRECT</td>\n",
+ " <td>NOUN</td>\n",
+ " <td>przystanku</td>\n",
+ " <td>NOUN</td>\n",
+ " <td>stronÄ™</td>\n",
+ " </tr>\n",
+ " <tr>\n",
" <th>28</th>\n",
" <td>CORRECT</td>\n",
- " <td>ADP</td>\n",
- " <td>na</td>\n",
- " <td>ADP</td>\n",
- " <td>na</td>\n",
+ " <td>NOUN</td>\n",
+ " <td>vis</td>\n",
+ " <td>NOUN</td>\n",
+ " <td>gocławia</td>\n",
" </tr>\n",
" <tr>\n",
" <th>29</th>\n",
- " <td>CORRECT</td>\n",
- " <td>PROPN</td>\n",
- " <td>ZwierzynieckÄ…</td>\n",
+ " <td>DELETION</td>\n",
" <td>PROPN</td>\n",
- " <td>zwierzynieckÄ…</td>\n",
+ " <td>-</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
" </tr>\n",
" <tr>\n",
" <th>30</th>\n",
- " <td>CORRECT</td>\n",
- " <td>ADP</td>\n",
- " <td>na</td>\n",
- " <td>ADP</td>\n",
- " <td>na</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>31</th>\n",
- " <td>CORRECT</td>\n",
- " <td>PROPN</td>\n",
- " <td>ZwierzynieckÄ…</td>\n",
+ " <td>DELETION</td>\n",
" <td>PROPN</td>\n",
- " <td>zwierzynieckÄ…</td>\n",
+ " <td>a</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
" </tr>\n",
" <tr>\n",
- " <th>32</th>\n",
+ " <th>31</th>\n",
" <td>SUBSTITUTION</td>\n",
- " <td>CCONJ</td>\n",
- " <td>a</td>\n",
- " <td>PRON</td>\n",
- " <td>ja</td>\n",
+ " <td>PUNCT</td>\n",
+ " <td>-</td>\n",
+ " <td>NOUN</td>\n",
+ " <td>przystanku</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>33</th>\n",
- " <td>CORRECT</td>\n",
- " <td>ADP</td>\n",
- " <td>z</td>\n",
+ " <th>32</th>\n",
+ " <td>SUBSTITUTION</td>\n",
" <td>ADP</td>\n",
- " <td>z</td>\n",
+ " <td>vis</td>\n",
+ " <td>NOUN</td>\n",
+ " <td>widzowi</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>34</th>\n",
+ " <th>33</th>\n",
" <td>SUBSTITUTION</td>\n",
" <td>PROPN</td>\n",
- " <td>Bródna</td>\n",
+ " <td>ZUSu</td>\n",
" <td>NOUN</td>\n",
- " <td>bródna</td>\n",
+ " <td>zusu</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>35</th>\n",
+ " <th>34</th>\n",
" <td>CORRECT</td>\n",
- " <td>ADP</td>\n",
- " <td>z</td>\n",
- " <td>ADP</td>\n",
- " <td>z</td>\n",
+ " <td>ADV</td>\n",
+ " <td>tak</td>\n",
+ " <td>ADV</td>\n",
+ " <td>tak</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>35</th>\n",
+ " <td>DELETION</td>\n",
+ " <td>PUNCT</td>\n",
+ " <td>?</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
" </tr>\n",
" <tr>\n",
" <th>36</th>\n",
" <td>CORRECT</td>\n",
- " <td>DET</td>\n",
- " <td>którego</td>\n",
- " <td>DET</td>\n",
- " <td>którego</td>\n",
+ " <td>PART</td>\n",
+ " <td>no</td>\n",
+ " <td>PART</td>\n",
+ " <td>no</td>\n",
" </tr>\n",
" <tr>\n",
" <th>37</th>\n",
" <td>CORRECT</td>\n",
- " <td>NOUN</td>\n",
- " <td>miejsca</td>\n",
- " <td>NOUN</td>\n",
- " <td>miejsca</td>\n",
+ " <td>PART</td>\n",
+ " <td>nie</td>\n",
+ " <td>PART</td>\n",
+ " <td>nie</td>\n",
" </tr>\n",
" <tr>\n",
" <th>38</th>\n",
- " <td>DELETION</td>\n",
- " <td>PUNCT</td>\n",
- " <td>?</td>\n",
- " <td></td>\n",
- " <td></td>\n",
+ " <td>CORRECT</td>\n",
+ " <td>PART</td>\n",
+ " <td>nie</td>\n",
+ " <td>PART</td>\n",
+ " <td>nie</td>\n",
" </tr>\n",
" <tr>\n",
" <th>39</th>\n",
" <td>CORRECT</td>\n",
- " <td>ADP</td>\n",
- " <td>z</td>\n",
- " <td>ADP</td>\n",
- " <td>z</td>\n",
+ " <td>ADV</td>\n",
+ " <td>tam</td>\n",
+ " <td>ADV</td>\n",
+ " <td>tam</td>\n",
" </tr>\n",
" <tr>\n",
" <th>40</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>PROPN</td>\n",
- " <td>Bródna</td>\n",
+ " <td>CORRECT</td>\n",
+ " <td>NOUN</td>\n",
+ " <td>vis</td>\n",
" <td>NOUN</td>\n",
- " <td>bródna</td>\n",
+ " <td>widzowi</td>\n",
" </tr>\n",
" <tr>\n",
" <th>41</th>\n",
- " <td>CORRECT</td>\n",
- " <td>AUX</td>\n",
- " <td>to</td>\n",
- " <td>AUX</td>\n",
- " <td>to</td>\n",
+ " <td>DELETION</td>\n",
+ " <td>PROPN</td>\n",
+ " <td>-</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
" </tr>\n",
" <tr>\n",
" <th>42</th>\n",
- " <td>CORRECT</td>\n",
- " <td>AUX</td>\n",
- " <td>jest</td>\n",
- " <td>AUX</td>\n",
- " <td>jest</td>\n",
+ " <td>DELETION</td>\n",
+ " <td>PROPN</td>\n",
+ " <td>a</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
" </tr>\n",
" <tr>\n",
" <th>43</th>\n",
- " <td>CORRECT</td>\n",
- " <td>NOUN</td>\n",
- " <td>ulica</td>\n",
- " <td>NOUN</td>\n",
- " <td>ulica</td>\n",
+ " <td>DELETION</td>\n",
+ " <td>PUNCT</td>\n",
+ " <td>-</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
" </tr>\n",
" <tr>\n",
" <th>44</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>PROPN</td>\n",
- " <td>Wyszogrodzka</td>\n",
- " <td>ADJ</td>\n",
- " <td>wyszogrodzka</td>\n",
+ " <td>DELETION</td>\n",
+ " <td>VERB</td>\n",
+ " <td>vis</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
" </tr>\n",
" <tr>\n",
" <th>45</th>\n",
- " <td>CORRECT</td>\n",
- " <td>ADV</td>\n",
- " <td>tu</td>\n",
- " <td>ADV</td>\n",
- " <td>tu</td>\n",
+ " <td>SUBSTITUTION</td>\n",
+ " <td>VERB</td>\n",
+ " <td>Panoramy</td>\n",
+ " <td>NOUN</td>\n",
+ " <td>panoramy</td>\n",
" </tr>\n",
" <tr>\n",
" <th>46</th>\n",
" <td>CORRECT</td>\n",
" <td>ADP</td>\n",
- " <td>przy</td>\n",
+ " <td>przez</td>\n",
" <td>ADP</td>\n",
- " <td>przy</td>\n",
+ " <td>przez</td>\n",
" </tr>\n",
" <tr>\n",
" <th>47</th>\n",
" <td>SUBSTITUTION</td>\n",
" <td>PROPN</td>\n",
- " <td>Rembielińskiej</td>\n",
+ " <td>Siekierkowski</td>\n",
" <td>ADJ</td>\n",
- " <td>rembielińskiej</td>\n",
+ " <td>siekierkowski</td>\n",
" </tr>\n",
" <tr>\n",
" <th>48</th>\n",
" <td>CORRECT</td>\n",
- " <td>CCONJ</td>\n",
- " <td>czyli</td>\n",
- " <td>CCONJ</td>\n",
- " <td>czyli</td>\n",
+ " <td>ADV</td>\n",
+ " <td>tam</td>\n",
+ " <td>ADV</td>\n",
+ " <td>tam</td>\n",
" </tr>\n",
" <tr>\n",
" <th>49</th>\n",
" <td>CORRECT</td>\n",
" <td>ADP</td>\n",
- " <td>przy</td>\n",
+ " <td>w</td>\n",
" <td>ADP</td>\n",
- " <td>przy</td>\n",
+ " <td>w</td>\n",
" </tr>\n",
" <tr>\n",
" <th>50</th>\n",
" <td>CORRECT</td>\n",
" <td>NOUN</td>\n",
- " <td>tramwajach</td>\n",
+ " <td>stronÄ™</td>\n",
" <td>NOUN</td>\n",
- " <td>tramwajach</td>\n",
+ " <td>stronÄ™</td>\n",
" </tr>\n",
" <tr>\n",
" <th>51</th>\n",
- " <td>DELETION</td>\n",
- " <td>ADV</td>\n",
- " <td>tak</td>\n",
- " <td></td>\n",
- " <td></td>\n",
+ " <td>SUBSTITUTION</td>\n",
+ " <td>PROPN</td>\n",
+ " <td>Gocławia</td>\n",
+ " <td>VERB</td>\n",
+ " <td>gocławia</td>\n",
" </tr>\n",
" <tr>\n",
" <th>52</th>\n",
- " <td>DELETION</td>\n",
- " <td>PUNCT</td>\n",
- " <td>?</td>\n",
- " <td></td>\n",
- " <td></td>\n",
+ " <td>CORRECT</td>\n",
+ " <td>CCONJ</td>\n",
+ " <td>ale</td>\n",
+ " <td>CCONJ</td>\n",
+ " <td>ale</td>\n",
" </tr>\n",
" <tr>\n",
" <th>53</th>\n",
" <td>CORRECT</td>\n",
- " <td>ADP</td>\n",
- " <td>przy</td>\n",
- " <td>ADP</td>\n",
- " <td>przy</td>\n",
+ " <td>PRON</td>\n",
+ " <td>to</td>\n",
+ " <td>PRON</td>\n",
+ " <td>to</td>\n",
" </tr>\n",
" <tr>\n",
" <th>54</th>\n",
" <td>CORRECT</td>\n",
- " <td>NOUN</td>\n",
- " <td>tramwajach</td>\n",
- " <td>NOUN</td>\n",
- " <td>tramwajach</td>\n",
+ " <td>PART</td>\n",
+ " <td>nie</td>\n",
+ " <td>PART</td>\n",
+ " <td>nie</td>\n",
" </tr>\n",
" <tr>\n",
" <th>55</th>\n",
" <td>CORRECT</td>\n",
- " <td>ADV</td>\n",
- " <td>tak</td>\n",
- " <td>ADV</td>\n",
- " <td>tak</td>\n",
+ " <td>ADP</td>\n",
+ " <td>z</td>\n",
+ " <td>ADP</td>\n",
+ " <td>z</td>\n",
" </tr>\n",
" <tr>\n",
" <th>56</th>\n",
- " <td>DELETION</td>\n",
- " <td>VERB</td>\n",
- " <td>może</td>\n",
- " <td></td>\n",
- " <td></td>\n",
+ " <td>CORRECT</td>\n",
+ " <td>DET</td>\n",
+ " <td>tego</td>\n",
+ " <td>DET</td>\n",
+ " <td>tego</td>\n",
" </tr>\n",
" <tr>\n",
" <th>57</th>\n",
- " <td>DELETION</td>\n",
+ " <td>CORRECT</td>\n",
" <td>NOUN</td>\n",
- " <td>pani</td>\n",
- " <td></td>\n",
- " <td></td>\n",
+ " <td>przystanku</td>\n",
+ " <td>NOUN</td>\n",
+ " <td>przystanku</td>\n",
" </tr>\n",
" <tr>\n",
" <th>58</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>VERB</td>\n",
- " <td>poczeka</td>\n",
- " <td>PART</td>\n",
- " <td>może</td>\n",
+ " <td>CORRECT</td>\n",
+ " <td>NOUN</td>\n",
+ " <td>Aleja</td>\n",
+ " <td>NOUN</td>\n",
+ " <td>aleja</td>\n",
" </tr>\n",
" <tr>\n",
" <th>59</th>\n",
- " <td>CORRECT</td>\n",
- " <td>VERB</td>\n",
- " <td>sprawdzÄ™</td>\n",
- " <td>VERB</td>\n",
- " <td>sprawdzÄ™</td>\n",
+ " <td>DELETION</td>\n",
+ " <td>PROPN</td>\n",
+ " <td>Witosa</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
" </tr>\n",
" <tr>\n",
" <th>60</th>\n",
- " <td>CORRECT</td>\n",
- " <td>ADV</td>\n",
- " <td>dobrze</td>\n",
- " <td>ADV</td>\n",
- " <td>dobrze</td>\n",
+ " <td>SUBSTITUTION</td>\n",
+ " <td>PUNCT</td>\n",
+ " <td>?</td>\n",
+ " <td>NOUN</td>\n",
+ " <td>witosa</td>\n",
" </tr>\n",
" <tr>\n",
" <th>61</th>\n",
" <td>CORRECT</td>\n",
- " <td>ADV</td>\n",
- " <td>dobrze</td>\n",
- " <td>ADV</td>\n",
- " <td>dobrze</td>\n",
+ " <td>PART</td>\n",
+ " <td>no</td>\n",
+ " <td>PART</td>\n",
+ " <td>no</td>\n",
" </tr>\n",
" <tr>\n",
" <th>62</th>\n",
- " <td>DELETION</td>\n",
- " <td>NOUN</td>\n",
- " <td>pani</td>\n",
- " <td></td>\n",
- " <td></td>\n",
+ " <td>CORRECT</td>\n",
+ " <td>AUX</td>\n",
+ " <td>to</td>\n",
+ " <td>AUX</td>\n",
+ " <td>to</td>\n",
" </tr>\n",
" <tr>\n",
" <th>63</th>\n",
- " <td>DELETION</td>\n",
- " <td>PRON</td>\n",
- " <td>sobie</td>\n",
- " <td></td>\n",
- " <td></td>\n",
+ " <td>SUBSTITUTION</td>\n",
+ " <td>VERB</td>\n",
+ " <td>jest</td>\n",
+ " <td>AUX</td>\n",
+ " <td>jest</td>\n",
" </tr>\n",
" <tr>\n",
" <th>64</th>\n",
- " <td>CORRECT</td>\n",
- " <td>VERB</td>\n",
- " <td>podjedzie</td>\n",
- " <td>VERB</td>\n",
- " <td>podjedzie</td>\n",
+ " <td>SUBSTITUTION</td>\n",
+ " <td>CCONJ</td>\n",
+ " <td>czy</td>\n",
+ " <td>PART</td>\n",
+ " <td>czy</td>\n",
" </tr>\n",
" <tr>\n",
" <th>65</th>\n",
- " <td>CORRECT</td>\n",
- " <td>NOUN</td>\n",
- " <td>tramwajem</td>\n",
+ " <td>SUBSTITUTION</td>\n",
+ " <td>PROPN</td>\n",
+ " <td>Bartoszka</td>\n",
" <td>NOUN</td>\n",
- " <td>tramwajem</td>\n",
+ " <td>bartoszka</td>\n",
" </tr>\n",
" <tr>\n",
" <th>66</th>\n",
" <td>CORRECT</td>\n",
" <td>ADP</td>\n",
- " <td>do</td>\n",
+ " <td>na</td>\n",
" <td>ADP</td>\n",
- " <td>do</td>\n",
+ " <td>na</td>\n",
" </tr>\n",
" <tr>\n",
" <th>67</th>\n",
" <td>CORRECT</td>\n",
" <td>NOUN</td>\n",
- " <td>Ronda</td>\n",
+ " <td>żądanie</td>\n",
" <td>NOUN</td>\n",
- " <td>ronda</td>\n",
+ " <td>żądanie</td>\n",
" </tr>\n",
" <tr>\n",
" <th>68</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>PROPN</td>\n",
- " <td>Żaba</td>\n",
- " <td>NOUN</td>\n",
- " <td>żaba</td>\n",
+ " <td>CORRECT</td>\n",
+ " <td>VERB</td>\n",
+ " <td>wie</td>\n",
+ " <td>VERB</td>\n",
+ " <td>wie</td>\n",
" </tr>\n",
" <tr>\n",
" <th>69</th>\n",
" <td>CORRECT</td>\n",
- " <td>ADV</td>\n",
- " <td>tak</td>\n",
- " <td>ADV</td>\n",
- " <td>tak</td>\n",
+ " <td>NOUN</td>\n",
+ " <td>pan</td>\n",
+ " <td>NOUN</td>\n",
+ " <td>pan</td>\n",
" </tr>\n",
" <tr>\n",
" <th>70</th>\n",
" <td>CORRECT</td>\n",
- " <td>ADP</td>\n",
- " <td>od</td>\n",
- " <td>ADP</td>\n",
- " <td>od</td>\n",
+ " <td>ADV</td>\n",
+ " <td>gdzie</td>\n",
+ " <td>ADV</td>\n",
+ " <td>gdzie</td>\n",
" </tr>\n",
" <tr>\n",
" <th>71</th>\n",
" <td>CORRECT</td>\n",
- " <td>NOUN</td>\n",
- " <td>Ronda</td>\n",
- " <td>NOUN</td>\n",
- " <td>ronda</td>\n",
+ " <td>AUX</td>\n",
+ " <td>jest</td>\n",
+ " <td>AUX</td>\n",
+ " <td>jest</td>\n",
" </tr>\n",
" <tr>\n",
" <th>72</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>PROPN</td>\n",
- " <td>Żaba</td>\n",
- " <td>NOUN</td>\n",
- " <td>żaba</td>\n",
+ " <td>CORRECT</td>\n",
+ " <td>PRON</td>\n",
+ " <td>siÄ™</td>\n",
+ " <td>PRON</td>\n",
+ " <td>siÄ™</td>\n",
" </tr>\n",
" <tr>\n",
" <th>73</th>\n",
" <td>CORRECT</td>\n",
- " <td>PART</td>\n",
- " <td>już</td>\n",
- " <td>PART</td>\n",
- " <td>już</td>\n",
+ " <td>VERB</td>\n",
+ " <td>zaczyna</td>\n",
+ " <td>VERB</td>\n",
+ " <td>zaczyna</td>\n",
" </tr>\n",
" <tr>\n",
" <th>74</th>\n",
- " <td>DELETION</td>\n",
- " <td>NUM</td>\n",
- " <td>sto</td>\n",
- " <td></td>\n",
- " <td></td>\n",
+ " <td>CORRECT</td>\n",
+ " <td>NOUN</td>\n",
+ " <td>Most</td>\n",
+ " <td>NOUN</td>\n",
+ " <td>most</td>\n",
" </tr>\n",
" <tr>\n",
" <th>75</th>\n",
- " <td>DELETION</td>\n",
- " <td>NUM</td>\n",
- " <td>sześćdziesiąt</td>\n",
- " <td></td>\n",
- " <td></td>\n",
+ " <td>SUBSTITUTION</td>\n",
+ " <td>PROPN</td>\n",
+ " <td>Siekierkowski</td>\n",
+ " <td>ADJ</td>\n",
+ " <td>siekierkowski</td>\n",
" </tr>\n",
" <tr>\n",
" <th>76</th>\n",
- " <td>DELETION</td>\n",
- " <td>NUM</td>\n",
- " <td>dwa</td>\n",
- " <td></td>\n",
- " <td></td>\n",
+ " <td>CORRECT</td>\n",
+ " <td>ADV</td>\n",
+ " <td>tam</td>\n",
+ " <td>ADV</td>\n",
+ " <td>tam</td>\n",
" </tr>\n",
" <tr>\n",
" <th>77</th>\n",
- " <td>DELETION</td>\n",
- " <td>AUX</td>\n",
- " <td>jest</td>\n",
- " <td></td>\n",
- " <td></td>\n",
+ " <td>CORRECT</td>\n",
+ " <td>ADP</td>\n",
+ " <td>w</td>\n",
+ " <td>ADP</td>\n",
+ " <td>w</td>\n",
" </tr>\n",
" <tr>\n",
" <th>78</th>\n",
" <td>CORRECT</td>\n",
- " <td>NUM</td>\n",
- " <td>sto</td>\n",
- " <td>NUM</td>\n",
- " <td>162</td>\n",
+ " <td>NOUN</td>\n",
+ " <td>stronÄ™</td>\n",
+ " <td>NOUN</td>\n",
+ " <td>stronÄ™</td>\n",
" </tr>\n",
" <tr>\n",
" <th>79</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>NUM</td>\n",
- " <td>sześćdziesiąt</td>\n",
- " <td>VERB</td>\n",
- " <td>jest</td>\n",
+ " <td>CORRECT</td>\n",
+ " <td>PROPN</td>\n",
+ " <td>Gocławia</td>\n",
+ " <td>PROPN</td>\n",
+ " <td>wrocław</td>\n",
" </tr>\n",
" <tr>\n",
" <th>80</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>NUM</td>\n",
- " <td>dwa</td>\n",
- " <td>X</td>\n",
- " <td>162</td>\n",
+ " <td>DELETION</td>\n",
+ " <td>ADV</td>\n",
+ " <td>gdzie</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
" </tr>\n",
" <tr>\n",
" <th>81</th>\n",
- " <td>CORRECT</td>\n",
- " <td>ADV</td>\n",
- " <td>tak</td>\n",
- " <td>ADV</td>\n",
- " <td>tak</td>\n",
+ " <td>DELETION</td>\n",
+ " <td>VERB</td>\n",
+ " <td>ma</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
" </tr>\n",
" <tr>\n",
" <th>82</th>\n",
" <td>CORRECT</td>\n",
- " <td>CCONJ</td>\n",
- " <td>i</td>\n",
- " <td>CCONJ</td>\n",
- " <td>i</td>\n",
+ " <td>PRON</td>\n",
+ " <td>on</td>\n",
+ " <td>PRON</td>\n",
+ " <td>on</td>\n",
" </tr>\n",
" <tr>\n",
" <th>83</th>\n",
+ " <td>CORRECT</td>\n",
+ " <td>NOUN</td>\n",
+ " <td>przystanek</td>\n",
+ " <td>NOUN</td>\n",
+ " <td>przystanek</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>84</th>\n",
+ " <td>CORRECT</td>\n",
+ " <td>ADJ</td>\n",
+ " <td>pierwszy</td>\n",
+ " <td>ADJ</td>\n",
+ " <td>pierwszy</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>85</th>\n",
" <td>DELETION</td>\n",
" <td>NUM</td>\n",
" <td>sto</td>\n",
@@ -2656,511 +2173,471 @@
" <td></td>\n",
" </tr>\n",
" <tr>\n",
- " <th>84</th>\n",
+ " <th>86</th>\n",
" <td>DELETION</td>\n",
- " <td>NUM</td>\n",
- " <td>sześćdziesiąt</td>\n",
+ " <td>PROPN</td>\n",
+ " <td>czterdzieści</td>\n",
" <td></td>\n",
" <td></td>\n",
" </tr>\n",
" <tr>\n",
- " <th>85</th>\n",
- " <td>CORRECT</td>\n",
- " <td>NUM</td>\n",
- " <td>dwa</td>\n",
+ " <th>87</th>\n",
+ " <td>SUBSTITUTION</td>\n",
" <td>NUM</td>\n",
- " <td>162</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>86</th>\n",
- " <td>CORRECT</td>\n",
- " <td>ADV</td>\n",
- " <td>tam</td>\n",
- " <td>ADV</td>\n",
- " <td>tam</td>\n",
+ " <td>trzy</td>\n",
+ " <td>X</td>\n",
+ " <td>143</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>87</th>\n",
+ " <th>88</th>\n",
" <td>CORRECT</td>\n",
" <td>VERB</td>\n",
- " <td>dojadÄ™</td>\n",
+ " <td>znaczy</td>\n",
" <td>VERB</td>\n",
- " <td>dojadÄ™</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>88</th>\n",
- " <td>CORRECT</td>\n",
- " <td>ADP</td>\n",
- " <td>do</td>\n",
- " <td>ADP</td>\n",
- " <td>do</td>\n",
+ " <td>znaczy</td>\n",
" </tr>\n",
" <tr>\n",
" <th>89</th>\n",
" <td>CORRECT</td>\n",
- " <td>DET</td>\n",
- " <td>tej</td>\n",
- " <td>DET</td>\n",
- " <td>tej</td>\n",
+ " <td>PART</td>\n",
+ " <td>tak</td>\n",
+ " <td>PART</td>\n",
+ " <td>tak</td>\n",
" </tr>\n",
" <tr>\n",
" <th>90</th>\n",
" <td>CORRECT</td>\n",
- " <td>NOUN</td>\n",
- " <td>ulicy</td>\n",
- " <td>NOUN</td>\n",
- " <td>uli</td>\n",
+ " <td>PART</td>\n",
+ " <td>naprawdÄ™</td>\n",
+ " <td>PART</td>\n",
+ " <td>naprawdÄ™</td>\n",
" </tr>\n",
" <tr>\n",
" <th>91</th>\n",
" <td>CORRECT</td>\n",
- " <td>ADV</td>\n",
- " <td>tak</td>\n",
- " <td>ADV</td>\n",
- " <td>tak</td>\n",
+ " <td>NOUN</td>\n",
+ " <td>Most</td>\n",
+ " <td>NOUN</td>\n",
+ " <td>most</td>\n",
" </tr>\n",
" <tr>\n",
" <th>92</th>\n",
" <td>CORRECT</td>\n",
- " <td>VERB</td>\n",
- " <td>może</td>\n",
- " <td>VERB</td>\n",
- " <td>może</td>\n",
+ " <td>ADJ</td>\n",
+ " <td>Siekierkowski</td>\n",
+ " <td>ADJ</td>\n",
+ " <td>siekierkowski</td>\n",
" </tr>\n",
" <tr>\n",
" <th>93</th>\n",
" <td>CORRECT</td>\n",
- " <td>NOUN</td>\n",
- " <td>pani</td>\n",
- " <td>NOUN</td>\n",
- " <td>pani</td>\n",
+ " <td>AUX</td>\n",
+ " <td>to</td>\n",
+ " <td>AUX</td>\n",
+ " <td>to</td>\n",
" </tr>\n",
" <tr>\n",
" <th>94</th>\n",
" <td>CORRECT</td>\n",
- " <td>VERB</td>\n",
- " <td>wysiąść</td>\n",
- " <td>VERB</td>\n",
- " <td>wysiąść</td>\n",
+ " <td>PRON</td>\n",
+ " <td>siÄ™</td>\n",
+ " <td>PRON</td>\n",
+ " <td>siÄ™</td>\n",
" </tr>\n",
" <tr>\n",
" <th>95</th>\n",
- " <td>DELETION</td>\n",
- " <td>ADP</td>\n",
- " <td>na</td>\n",
- " <td></td>\n",
- " <td></td>\n",
+ " <td>CORRECT</td>\n",
+ " <td>VERB</td>\n",
+ " <td>zaczyna</td>\n",
+ " <td>VERB</td>\n",
+ " <td>zaczyna</td>\n",
" </tr>\n",
" <tr>\n",
" <th>96</th>\n",
" <td>CORRECT</td>\n",
- " <td>NOUN</td>\n",
- " <td>przystanku</td>\n",
- " <td>NOUN</td>\n",
- " <td>banku</td>\n",
+ " <td>ADP</td>\n",
+ " <td>za</td>\n",
+ " <td>ADP</td>\n",
+ " <td>za</td>\n",
" </tr>\n",
" <tr>\n",
" <th>97</th>\n",
- " <td>CORRECT</td>\n",
- " <td>PROPN</td>\n",
- " <td>Bartycka</td>\n",
+ " <td>SUBSTITUTION</td>\n",
" <td>PROPN</td>\n",
- " <td>bartycka</td>\n",
+ " <td>Siekierki</td>\n",
+ " <td>NOUN</td>\n",
+ " <td>siekierki</td>\n",
" </tr>\n",
" <tr>\n",
" <th>98</th>\n",
" <td>CORRECT</td>\n",
- " <td>CCONJ</td>\n",
- " <td>albo</td>\n",
- " <td>CCONJ</td>\n",
- " <td>albo</td>\n",
+ " <td>NOUN</td>\n",
+ " <td>Sanktuarium</td>\n",
+ " <td>NOUN</td>\n",
+ " <td>sanktuarium</td>\n",
" </tr>\n",
" <tr>\n",
" <th>99</th>\n",
" <td>CORRECT</td>\n",
- " <td>PROPN</td>\n",
- " <td>Sielce</td>\n",
- " <td>PROPN</td>\n",
- " <td>sielce</td>\n",
+ " <td>PART</td>\n",
+ " <td>no</td>\n",
+ " <td>PART</td>\n",
+ " <td>no</td>\n",
" </tr>\n",
" <tr>\n",
" <th>100</th>\n",
" <td>CORRECT</td>\n",
- " <td>PROPN</td>\n",
- " <td>Bartycka</td>\n",
- " <td>PROPN</td>\n",
- " <td>bartycka</td>\n",
+ " <td>ADV</td>\n",
+ " <td>właśnie</td>\n",
+ " <td>ADV</td>\n",
+ " <td>właśnie</td>\n",
" </tr>\n",
" <tr>\n",
" <th>101</th>\n",
" <td>CORRECT</td>\n",
- " <td>CCONJ</td>\n",
- " <td>albo</td>\n",
- " <td>CCONJ</td>\n",
- " <td>albo</td>\n",
+ " <td>ADP</td>\n",
+ " <td>przed</td>\n",
+ " <td>ADP</td>\n",
+ " <td>przed</td>\n",
" </tr>\n",
" <tr>\n",
" <th>102</th>\n",
- " <td>DELETION</td>\n",
- " <td>PUNCT</td>\n",
- " <td>?</td>\n",
- " <td></td>\n",
- " <td></td>\n",
+ " <td>CORRECT</td>\n",
+ " <td>PRON</td>\n",
+ " <td>tym</td>\n",
+ " <td>PRON</td>\n",
+ " <td>tym</td>\n",
" </tr>\n",
" <tr>\n",
" <th>103</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>PROPN</td>\n",
- " <td>Sielce</td>\n",
- " <td>NOUN</td>\n",
- " <td>sielce</td>\n",
- " </tr>\n",
- " <tr>\n",
+ " <td>CORRECT</td>\n",
+ " <td>ADP</td>\n",
+ " <td>przed</td>\n",
+ " <td>ADP</td>\n",
+ " <td>przed</td>\n",
+ " </tr>\n",
+ " <tr>\n",
" <th>104</th>\n",
" <td>CORRECT</td>\n",
- " <td>PROPN</td>\n",
- " <td>Sielce</td>\n",
- " <td>PROPN</td>\n",
- " <td>sielce</td>\n",
+ " <td>PRON</td>\n",
+ " <td>tym</td>\n",
+ " <td>PRON</td>\n",
+ " <td>tym</td>\n",
" </tr>\n",
" <tr>\n",
" <th>105</th>\n",
" <td>CORRECT</td>\n",
- " <td>ADV</td>\n",
- " <td>tak</td>\n",
- " <td>ADV</td>\n",
- " <td>tak</td>\n",
+ " <td>NOUN</td>\n",
+ " <td>przystanek</td>\n",
+ " <td>NOUN</td>\n",
+ " <td>przystanek</td>\n",
" </tr>\n",
" <tr>\n",
" <th>106</th>\n",
- " <td>DELETION</td>\n",
- " <td>PUNCT</td>\n",
- " <td>?</td>\n",
- " <td></td>\n",
- " <td></td>\n",
+ " <td>CORRECT</td>\n",
+ " <td>ADP</td>\n",
+ " <td>o</td>\n",
+ " <td>ADP</td>\n",
+ " <td>o</td>\n",
" </tr>\n",
" <tr>\n",
" <th>107</th>\n",
" <td>CORRECT</td>\n",
- " <td>ADV</td>\n",
- " <td>tak</td>\n",
- " <td>ADV</td>\n",
- " <td>tak</td>\n",
+ " <td>DET</td>\n",
+ " <td>której</td>\n",
+ " <td>DET</td>\n",
+ " <td>której</td>\n",
" </tr>\n",
" <tr>\n",
" <th>108</th>\n",
" <td>CORRECT</td>\n",
- " <td>X</td>\n",
- " <td>aha</td>\n",
- " <td>X</td>\n",
- " <td>aha</td>\n",
+ " <td>VERB</td>\n",
+ " <td>jest</td>\n",
+ " <td>VERB</td>\n",
+ " <td>jest</td>\n",
" </tr>\n",
" <tr>\n",
" <th>109</th>\n",
- " <td>CORRECT</td>\n",
- " <td>CCONJ</td>\n",
- " <td>i</td>\n",
- " <td>CCONJ</td>\n",
- " <td>i</td>\n",
+ " <td>DELETION</td>\n",
+ " <td>NUM</td>\n",
+ " <td>sto</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
" </tr>\n",
" <tr>\n",
" <th>110</th>\n",
- " <td>CORRECT</td>\n",
- " <td>ADV</td>\n",
- " <td>tam</td>\n",
- " <td>ADV</td>\n",
- " <td>tam</td>\n",
+ " <td>DELETION</td>\n",
+ " <td>NUM</td>\n",
+ " <td>czterdzieści</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
" </tr>\n",
" <tr>\n",
" <th>111</th>\n",
- " <td>CORRECT</td>\n",
- " <td>ADP</td>\n",
- " <td>w</td>\n",
- " <td>ADP</td>\n",
- " <td>w</td>\n",
+ " <td>SUBSTITUTION</td>\n",
+ " <td>NUM</td>\n",
+ " <td>trzy</td>\n",
+ " <td>X</td>\n",
+ " <td>143</td>\n",
" </tr>\n",
" <tr>\n",
" <th>112</th>\n",
" <td>CORRECT</td>\n",
- " <td>NOUN</td>\n",
- " <td>pobliżu</td>\n",
- " <td>NOUN</td>\n",
- " <td>pobliżu</td>\n",
+ " <td>ADJ</td>\n",
+ " <td>najbliższy</td>\n",
+ " <td>ADJ</td>\n",
+ " <td>najbliższy</td>\n",
" </tr>\n",
" <tr>\n",
" <th>113</th>\n",
- " <td>CORRECT</td>\n",
- " <td>AUX</td>\n",
- " <td>jest</td>\n",
- " <td>AUX</td>\n",
- " <td>jest</td>\n",
+ " <td>DELETION</td>\n",
+ " <td>NOUN</td>\n",
+ " <td>aha</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
" </tr>\n",
" <tr>\n",
" <th>114</th>\n",
- " <td>CORRECT</td>\n",
- " <td>DET</td>\n",
- " <td>ta</td>\n",
- " <td>DET</td>\n",
- " <td>ta</td>\n",
+ " <td>DELETION</td>\n",
+ " <td>CCONJ</td>\n",
+ " <td>czyli</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
" </tr>\n",
" <tr>\n",
" <th>115</th>\n",
- " <td>CORRECT</td>\n",
- " <td>NOUN</td>\n",
- " <td>ulica</td>\n",
- " <td>NOUN</td>\n",
- " <td>ulica</td>\n",
+ " <td>DELETION</td>\n",
+ " <td>PART</td>\n",
+ " <td>to</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
" </tr>\n",
" <tr>\n",
" <th>116</th>\n",
- " <td>DELETION</td>\n",
+ " <td>CORRECT</td>\n",
" <td>ADV</td>\n",
- " <td>tak</td>\n",
- " <td></td>\n",
- " <td></td>\n",
+ " <td>wtedy</td>\n",
+ " <td>ADV</td>\n",
+ " <td>wtedy</td>\n",
" </tr>\n",
" <tr>\n",
" <th>117</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>PUNCT</td>\n",
- " <td>?</td>\n",
- " <td>ADJ</td>\n",
- " <td>zwierzyniecka</td>\n",
+ " <td>CORRECT</td>\n",
+ " <td>NOUN</td>\n",
+ " <td>przystanek</td>\n",
+ " <td>NOUN</td>\n",
+ " <td>przystanek</td>\n",
" </tr>\n",
" <tr>\n",
" <th>118</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>CCONJ</td>\n",
- " <td>a</td>\n",
- " <td>VERB</td>\n",
- " <td>ma</td>\n",
+ " <td>CORRECT</td>\n",
+ " <td>ADJ</td>\n",
+ " <td>Małe</td>\n",
+ " <td>ADJ</td>\n",
+ " <td>małe</td>\n",
" </tr>\n",
" <tr>\n",
" <th>119</th>\n",
- " <td>CORRECT</td>\n",
- " <td>NOUN</td>\n",
- " <td>Zwierzyniecka</td>\n",
+ " <td>SUBSTITUTION</td>\n",
+ " <td>PROPN</td>\n",
+ " <td>Siekierki</td>\n",
" <td>NOUN</td>\n",
- " <td>pani</td>\n",
+ " <td>siekierki</td>\n",
" </tr>\n",
" <tr>\n",
" <th>120</th>\n",
" <td>CORRECT</td>\n",
- " <td>ADJ</td>\n",
- " <td>wysoki</td>\n",
- " <td>ADJ</td>\n",
- " <td>zwierzyniecka</td>\n",
+ " <td>CCONJ</td>\n",
+ " <td>ale</td>\n",
+ " <td>CCONJ</td>\n",
+ " <td>ale</td>\n",
" </tr>\n",
" <tr>\n",
" <th>121</th>\n",
" <td>CORRECT</td>\n",
- " <td>NOUN</td>\n",
- " <td>numer</td>\n",
- " <td>NOUN</td>\n",
- " <td>telefonem</td>\n",
+ " <td>AUX</td>\n",
+ " <td>to</td>\n",
+ " <td>AUX</td>\n",
+ " <td>to</td>\n",
" </tr>\n",
" <tr>\n",
" <th>122</th>\n",
+ " <td>CORRECT</td>\n",
+ " <td>PART</td>\n",
+ " <td>nie</td>\n",
+ " <td>PART</td>\n",
+ " <td>nie</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>123</th>\n",
" <td>DELETION</td>\n",
" <td>VERB</td>\n",
- " <td>ma</td>\n",
+ " <td>jest</td>\n",
" <td></td>\n",
" <td></td>\n",
" </tr>\n",
" <tr>\n",
- " <th>123</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>NOUN</td>\n",
- " <td>pani</td>\n",
- " <td>ADJ</td>\n",
- " <td>dzikie</td>\n",
- " </tr>\n",
- " <tr>\n",
" <th>124</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>PUNCT</td>\n",
- " <td>?</td>\n",
- " <td>DET</td>\n",
- " <td>który</td>\n",
+ " <td>DELETION</td>\n",
+ " <td>ADV</td>\n",
+ " <td>tak</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
" </tr>\n",
" <tr>\n",
" <th>125</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>PROPN</td>\n",
- " <td>Zwierzyniecka</td>\n",
- " <td>X</td>\n",
- " <td>8</td>\n",
+ " <td>DELETION</td>\n",
+ " <td>ADV</td>\n",
+ " <td>tak</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
" </tr>\n",
" <tr>\n",
" <th>126</th>\n",
- " <td>SUBSTITUTION</td>\n",
+ " <td>DELETION</td>\n",
" <td>ADV</td>\n",
- " <td>zaraz</td>\n",
- " <td>CCONJ</td>\n",
- " <td>a</td>\n",
+ " <td>tak</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
" </tr>\n",
" <tr>\n",
" <th>127</th>\n",
- " <td>CORRECT</td>\n",
- " <td>NOUN</td>\n",
- " <td>momencik</td>\n",
- " <td>NOUN</td>\n",
- " <td>zwierzyniecka</td>\n",
+ " <td>DELETION</td>\n",
+ " <td>ADV</td>\n",
+ " <td>tak</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
" </tr>\n",
" <tr>\n",
" <th>128</th>\n",
" <td>DELETION</td>\n",
- " <td>NUM</td>\n",
- " <td>osiem</td>\n",
+ " <td>ADP</td>\n",
+ " <td>na</td>\n",
" <td></td>\n",
" <td></td>\n",
" </tr>\n",
" <tr>\n",
" <th>129</th>\n",
- " <td>DELETION</td>\n",
- " <td>CCONJ</td>\n",
- " <td>A</td>\n",
- " <td></td>\n",
- " <td></td>\n",
+ " <td>SUBSTITUTION</td>\n",
+ " <td>NOUN</td>\n",
+ " <td>wysokości</td>\n",
+ " <td>AUX</td>\n",
+ " <td>jest</td>\n",
" </tr>\n",
" <tr>\n",
" <th>130</th>\n",
" <td>SUBSTITUTION</td>\n",
- " <td>PROPN</td>\n",
- " <td>Zwierzyniecka</td>\n",
- " <td>PRON</td>\n",
- " <td>to</td>\n",
+ " <td>NOUN</td>\n",
+ " <td>Panoramy</td>\n",
+ " <td>VERB</td>\n",
+ " <td>dokonać</td>\n",
" </tr>\n",
" <tr>\n",
" <th>131</th>\n",
" <td>CORRECT</td>\n",
- " <td>AUX</td>\n",
- " <td>to</td>\n",
- " <td>AUX</td>\n",
- " <td>to</td>\n",
+ " <td>NOUN</td>\n",
+ " <td>aha</td>\n",
+ " <td>NOUN</td>\n",
+ " <td>panoramy</td>\n",
" </tr>\n",
" <tr>\n",
" <th>132</th>\n",
- " <td>DELETION</td>\n",
- " <td>PRON</td>\n",
- " <td>to</td>\n",
- " <td></td>\n",
- " <td></td>\n",
+ " <td>CORRECT</td>\n",
+ " <td>ADV</td>\n",
+ " <td>dobrze</td>\n",
+ " <td>ADV</td>\n",
+ " <td>dobrze</td>\n",
" </tr>\n",
" <tr>\n",
" <th>133</th>\n",
" <td>CORRECT</td>\n",
- " <td>ADP</td>\n",
- " <td>przy</td>\n",
- " <td>ADP</td>\n",
- " <td>przy</td>\n",
+ " <td>ADJ</td>\n",
+ " <td>najbliższy</td>\n",
+ " <td>ADJ</td>\n",
+ " <td>najbliższy</td>\n",
" </tr>\n",
" <tr>\n",
" <th>134</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>PROPN</td>\n",
- " <td>Sielce</td>\n",
- " <td>NOUN</td>\n",
- " <td>sielce</td>\n",
+ " <td>CORRECT</td>\n",
+ " <td>PART</td>\n",
+ " <td>już</td>\n",
+ " <td>PART</td>\n",
+ " <td>już</td>\n",
" </tr>\n",
" <tr>\n",
" <th>135</th>\n",
" <td>CORRECT</td>\n",
" <td>NOUN</td>\n",
- " <td>trza</td>\n",
+ " <td>chwileczkÄ™</td>\n",
" <td>NOUN</td>\n",
- " <td>trza</td>\n",
+ " <td>chwileczkÄ™</td>\n",
" </tr>\n",
" <tr>\n",
" <th>136</th>\n",
" <td>CORRECT</td>\n",
- " <td>VERB</td>\n",
- " <td>wysiąść</td>\n",
- " <td>VERB</td>\n",
- " <td>wysiąść</td>\n",
+ " <td>ADJ</td>\n",
+ " <td>czternasta</td>\n",
+ " <td>ADJ</td>\n",
+ " <td>czternasta</td>\n",
" </tr>\n",
" <tr>\n",
" <th>137</th>\n",
- " <td>CORRECT</td>\n",
- " <td>ADP</td>\n",
- " <td>przy</td>\n",
- " <td>ADP</td>\n",
- " <td>przy</td>\n",
+ " <td>DELETION</td>\n",
+ " <td>NUM</td>\n",
+ " <td>czterdzieści</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
" </tr>\n",
" <tr>\n",
" <th>138</th>\n",
" <td>CORRECT</td>\n",
- " <td>PROPN</td>\n",
- " <td>Sielce</td>\n",
- " <td>PROPN</td>\n",
- " <td>sielce</td>\n",
+ " <td>NUM</td>\n",
+ " <td>sześć</td>\n",
+ " <td>NUM</td>\n",
+ " <td>46</td>\n",
" </tr>\n",
" <tr>\n",
" <th>139</th>\n",
" <td>CORRECT</td>\n",
- " <td>ADV</td>\n",
- " <td>tak</td>\n",
- " <td>ADV</td>\n",
- " <td>tak</td>\n",
+ " <td>ADJ</td>\n",
+ " <td>piętnasta</td>\n",
+ " <td>ADJ</td>\n",
+ " <td>piętnasta</td>\n",
" </tr>\n",
" <tr>\n",
" <th>140</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>PUNCT</td>\n",
- " <td>?</td>\n",
- " <td>ADV</td>\n",
- " <td>tak</td>\n",
+ " <td>DELETION</td>\n",
+ " <td>PART</td>\n",
+ " <td>zero</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
" </tr>\n",
" <tr>\n",
" <th>141</th>\n",
- " <td>CORRECT</td>\n",
- " <td>ADV</td>\n",
- " <td>tak</td>\n",
- " <td>ADV</td>\n",
- " <td>stanek</td>\n",
+ " <td>SUBSTITUTION</td>\n",
+ " <td>ADJ</td>\n",
+ " <td>jeden</td>\n",
+ " <td>X</td>\n",
+ " <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>142</th>\n",
" <td>CORRECT</td>\n",
- " <td>NOUN</td>\n",
- " <td>przystanek</td>\n",
- " <td>NOUN</td>\n",
- " <td>sielce</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>143</th>\n",
- " <td>DELETION</td>\n",
- " <td>PROPN</td>\n",
- " <td>Sielce</td>\n",
- " <td></td>\n",
- " <td></td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>144</th>\n",
- " <td>CORRECT</td>\n",
" <td>X</td>\n",
" <td>aha</td>\n",
" <td>X</td>\n",
- " <td>aha</td>\n",
+ " <td>1</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>145</th>\n",
- " <td>DELETION</td>\n",
- " <td>ADV</td>\n",
- " <td>tak</td>\n",
- " <td></td>\n",
- " <td></td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>146</th>\n",
+ " <th>143</th>\n",
" <td>CORRECT</td>\n",
" <td>PART</td>\n",
" <td>no</td>\n",
" <td>PART</td>\n",
- " <td>no</td>\n",
+ " <td>aha</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>147</th>\n",
+ " <th>144</th>\n",
" <td>CORRECT</td>\n",
" <td>ADV</td>\n",
" <td>dobrze</td>\n",
@@ -3168,1019 +2645,1455 @@
" <td>dobrze</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>148</th>\n",
- " <td>CORRECT</td>\n",
- " <td>CCONJ</td>\n",
- " <td>a</td>\n",
- " <td>CCONJ</td>\n",
- " <td>a</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>149</th>\n",
+ " <th>145</th>\n",
" <td>CORRECT</td>\n",
- " <td>PROPN</td>\n",
- " <td>Sielce</td>\n",
- " <td>PROPN</td>\n",
- " <td>sielce</td>\n",
+ " <td>VERB</td>\n",
+ " <td>dziękuję</td>\n",
+ " <td>VERB</td>\n",
+ " <td>dziękuję</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>150</th>\n",
+ " <th>146</th>\n",
" <td>DELETION</td>\n",
- " <td>PRON</td>\n",
- " <td>to</td>\n",
+ " <td>ADP</td>\n",
+ " <td>do</td>\n",
" <td></td>\n",
" <td></td>\n",
" </tr>\n",
" <tr>\n",
- " <th>151</th>\n",
+ " <th>147</th>\n",
" <td>DELETION</td>\n",
- " <td>VERB</td>\n",
- " <td>znaczy</td>\n",
+ " <td>NOUN</td>\n",
+ " <td>widzenia</td>\n",
" <td></td>\n",
" <td></td>\n",
" </tr>\n",
" <tr>\n",
- " <th>152</th>\n",
+ " <th>148</th>\n",
" <td>CORRECT</td>\n",
- " <td>DET</td>\n",
- " <td>jaka</td>\n",
- " <td>DET</td>\n",
- " <td>jaka</td>\n",
+ " <td>ADP</td>\n",
+ " <td>do</td>\n",
+ " <td>ADP</td>\n",
+ " <td>do</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>153</th>\n",
+ " <th>149</th>\n",
" <td>CORRECT</td>\n",
- " <td>AUX</td>\n",
- " <td>to</td>\n",
- " <td>AUX</td>\n",
- " <td>to</td>\n",
+ " <td>NOUN</td>\n",
+ " <td>widzenia</td>\n",
+ " <td>NOUN</td>\n",
+ " <td>widzenia</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ " step_type reference_word_pos reference_word_text hypothesis_word_pos \\\n",
+ "0 DELETION PRON xxx \n",
+ "1 CORRECT NOUN dzień NOUN \n",
+ "2 CORRECT ADJ dobry ADJ \n",
+ "3 CORRECT NOUN dzień NOUN \n",
+ "4 CORRECT ADJ dobry ADJ \n",
+ "5 CORRECT VERB proszÄ™ VERB \n",
+ "6 CORRECT NOUN pana NOUN \n",
+ "7 CORRECT PRON ja PRON \n",
+ "8 CORRECT VERB mam VERB \n",
+ "9 INSERTION NOUN \n",
+ "10 CORRECT ADP o ADP \n",
+ "11 CORRECT DET której DET \n",
+ "12 CORRECT VERB będzie VERB \n",
+ "13 DELETION NUM sto \n",
+ "14 DELETION ADJ czterdzieści \n",
+ "15 SUBSTITUTION NUM trzy X \n",
+ "16 CORRECT AUX będzie AUX \n",
+ "17 CORRECT ADJ najbliższy ADJ \n",
+ "18 CORRECT ADP z ADP \n",
+ "19 CORRECT NOUN Alei NOUN \n",
+ "20 CORRECT NOUN Alei NOUN \n",
+ "21 DELETION PROPN Witosa \n",
+ "22 DELETION ADP w \n",
+ "23 CORRECT NOUN stronÄ™ NOUN \n",
+ "24 SUBSTITUTION PROPN Gocławia NOUN \n",
+ "25 CORRECT ADP z ADP \n",
+ "26 DELETION DET tego \n",
+ "27 CORRECT NOUN przystanku NOUN \n",
+ "28 CORRECT NOUN vis NOUN \n",
+ "29 DELETION PROPN - \n",
+ "30 DELETION PROPN a \n",
+ "31 SUBSTITUTION PUNCT - NOUN \n",
+ "32 SUBSTITUTION ADP vis NOUN \n",
+ "33 SUBSTITUTION PROPN ZUSu NOUN \n",
+ "34 CORRECT ADV tak ADV \n",
+ "35 DELETION PUNCT ? \n",
+ "36 CORRECT PART no PART \n",
+ "37 CORRECT PART nie PART \n",
+ "38 CORRECT PART nie PART \n",
+ "39 CORRECT ADV tam ADV \n",
+ "40 CORRECT NOUN vis NOUN \n",
+ "41 DELETION PROPN - \n",
+ "42 DELETION PROPN a \n",
+ "43 DELETION PUNCT - \n",
+ "44 DELETION VERB vis \n",
+ "45 SUBSTITUTION VERB Panoramy NOUN \n",
+ "46 CORRECT ADP przez ADP \n",
+ "47 SUBSTITUTION PROPN Siekierkowski ADJ \n",
+ "48 CORRECT ADV tam ADV \n",
+ "49 CORRECT ADP w ADP \n",
+ "50 CORRECT NOUN stronÄ™ NOUN \n",
+ "51 SUBSTITUTION PROPN Gocławia VERB \n",
+ "52 CORRECT CCONJ ale CCONJ \n",
+ "53 CORRECT PRON to PRON \n",
+ "54 CORRECT PART nie PART \n",
+ "55 CORRECT ADP z ADP \n",
+ "56 CORRECT DET tego DET \n",
+ "57 CORRECT NOUN przystanku NOUN \n",
+ "58 CORRECT NOUN Aleja NOUN \n",
+ "59 DELETION PROPN Witosa \n",
+ "60 SUBSTITUTION PUNCT ? NOUN \n",
+ "61 CORRECT PART no PART \n",
+ "62 CORRECT AUX to AUX \n",
+ "63 SUBSTITUTION VERB jest AUX \n",
+ "64 SUBSTITUTION CCONJ czy PART \n",
+ "65 SUBSTITUTION PROPN Bartoszka NOUN \n",
+ "66 CORRECT ADP na ADP \n",
+ "67 CORRECT NOUN żądanie NOUN \n",
+ "68 CORRECT VERB wie VERB \n",
+ "69 CORRECT NOUN pan NOUN \n",
+ "70 CORRECT ADV gdzie ADV \n",
+ "71 CORRECT AUX jest AUX \n",
+ "72 CORRECT PRON siÄ™ PRON \n",
+ "73 CORRECT VERB zaczyna VERB \n",
+ "74 CORRECT NOUN Most NOUN \n",
+ "75 SUBSTITUTION PROPN Siekierkowski ADJ \n",
+ "76 CORRECT ADV tam ADV \n",
+ "77 CORRECT ADP w ADP \n",
+ "78 CORRECT NOUN stronÄ™ NOUN \n",
+ "79 CORRECT PROPN Gocławia PROPN \n",
+ "80 DELETION ADV gdzie \n",
+ "81 DELETION VERB ma \n",
+ "82 CORRECT PRON on PRON \n",
+ "83 CORRECT NOUN przystanek NOUN \n",
+ "84 CORRECT ADJ pierwszy ADJ \n",
+ "85 DELETION NUM sto \n",
+ "86 DELETION PROPN czterdzieści \n",
+ "87 SUBSTITUTION NUM trzy X \n",
+ "88 CORRECT VERB znaczy VERB \n",
+ "89 CORRECT PART tak PART \n",
+ "90 CORRECT PART naprawdÄ™ PART \n",
+ "91 CORRECT NOUN Most NOUN \n",
+ "92 CORRECT ADJ Siekierkowski ADJ \n",
+ "93 CORRECT AUX to AUX \n",
+ "94 CORRECT PRON siÄ™ PRON \n",
+ "95 CORRECT VERB zaczyna VERB \n",
+ "96 CORRECT ADP za ADP \n",
+ "97 SUBSTITUTION PROPN Siekierki NOUN \n",
+ "98 CORRECT NOUN Sanktuarium NOUN \n",
+ "99 CORRECT PART no PART \n",
+ "100 CORRECT ADV właśnie ADV \n",
+ "101 CORRECT ADP przed ADP \n",
+ "102 CORRECT PRON tym PRON \n",
+ "103 CORRECT ADP przed ADP \n",
+ "104 CORRECT PRON tym PRON \n",
+ "105 CORRECT NOUN przystanek NOUN \n",
+ "106 CORRECT ADP o ADP \n",
+ "107 CORRECT DET której DET \n",
+ "108 CORRECT VERB jest VERB \n",
+ "109 DELETION NUM sto \n",
+ "110 DELETION NUM czterdzieści \n",
+ "111 SUBSTITUTION NUM trzy X \n",
+ "112 CORRECT ADJ najbliższy ADJ \n",
+ "113 DELETION NOUN aha \n",
+ "114 DELETION CCONJ czyli \n",
+ "115 DELETION PART to \n",
+ "116 CORRECT ADV wtedy ADV \n",
+ "117 CORRECT NOUN przystanek NOUN \n",
+ "118 CORRECT ADJ Małe ADJ \n",
+ "119 SUBSTITUTION PROPN Siekierki NOUN \n",
+ "120 CORRECT CCONJ ale CCONJ \n",
+ "121 CORRECT AUX to AUX \n",
+ "122 CORRECT PART nie PART \n",
+ "123 DELETION VERB jest \n",
+ "124 DELETION ADV tak \n",
+ "125 DELETION ADV tak \n",
+ "126 DELETION ADV tak \n",
+ "127 DELETION ADV tak \n",
+ "128 DELETION ADP na \n",
+ "129 SUBSTITUTION NOUN wysokości AUX \n",
+ "130 SUBSTITUTION NOUN Panoramy VERB \n",
+ "131 CORRECT NOUN aha NOUN \n",
+ "132 CORRECT ADV dobrze ADV \n",
+ "133 CORRECT ADJ najbliższy ADJ \n",
+ "134 CORRECT PART już PART \n",
+ "135 CORRECT NOUN chwileczkÄ™ NOUN \n",
+ "136 CORRECT ADJ czternasta ADJ \n",
+ "137 DELETION NUM czterdzieści \n",
+ "138 CORRECT NUM sześć NUM \n",
+ "139 CORRECT ADJ piętnasta ADJ \n",
+ "140 DELETION PART zero \n",
+ "141 SUBSTITUTION ADJ jeden X \n",
+ "142 CORRECT X aha X \n",
+ "143 CORRECT PART no PART \n",
+ "144 CORRECT ADV dobrze ADV \n",
+ "145 CORRECT VERB dziękuję VERB \n",
+ "146 DELETION ADP do \n",
+ "147 DELETION NOUN widzenia \n",
+ "148 CORRECT ADP do ADP \n",
+ "149 CORRECT NOUN widzenia NOUN \n",
+ "\n",
+ " hypothesis_word_text \n",
+ "0 \n",
+ "1 dzień \n",
+ "2 dobry \n",
+ "3 dzień \n",
+ "4 dobry \n",
+ "5 proszÄ™ \n",
+ "6 pana \n",
+ "7 ja \n",
+ "8 mam \n",
+ "9 pytanie \n",
+ "10 o \n",
+ "11 której \n",
+ "12 będzie \n",
+ "13 \n",
+ "14 \n",
+ "15 143 \n",
+ "16 będzie \n",
+ "17 najbliższy \n",
+ "18 z \n",
+ "19 alei \n",
+ "20 witosa \n",
+ "21 \n",
+ "22 \n",
+ "23 alei \n",
+ "24 witosa \n",
+ "25 w \n",
+ "26 \n",
+ "27 stronÄ™ \n",
+ "28 gocławia \n",
+ "29 \n",
+ "30 \n",
+ "31 przystanku \n",
+ "32 widzowi \n",
+ "33 zusu \n",
+ "34 tak \n",
+ "35 \n",
+ "36 no \n",
+ "37 nie \n",
+ "38 nie \n",
+ "39 tam \n",
+ "40 widzowi \n",
+ "41 \n",
+ "42 \n",
+ "43 \n",
+ "44 \n",
+ "45 panoramy \n",
+ "46 przez \n",
+ "47 siekierkowski \n",
+ "48 tam \n",
+ "49 w \n",
+ "50 stronÄ™ \n",
+ "51 gocławia \n",
+ "52 ale \n",
+ "53 to \n",
+ "54 nie \n",
+ "55 z \n",
+ "56 tego \n",
+ "57 przystanku \n",
+ "58 aleja \n",
+ "59 \n",
+ "60 witosa \n",
+ "61 no \n",
+ "62 to \n",
+ "63 jest \n",
+ "64 czy \n",
+ "65 bartoszka \n",
+ "66 na \n",
+ "67 żądanie \n",
+ "68 wie \n",
+ "69 pan \n",
+ "70 gdzie \n",
+ "71 jest \n",
+ "72 siÄ™ \n",
+ "73 zaczyna \n",
+ "74 most \n",
+ "75 siekierkowski \n",
+ "76 tam \n",
+ "77 w \n",
+ "78 stronÄ™ \n",
+ "79 wrocław \n",
+ "80 \n",
+ "81 \n",
+ "82 on \n",
+ "83 przystanek \n",
+ "84 pierwszy \n",
+ "85 \n",
+ "86 \n",
+ "87 143 \n",
+ "88 znaczy \n",
+ "89 tak \n",
+ "90 naprawdÄ™ \n",
+ "91 most \n",
+ "92 siekierkowski \n",
+ "93 to \n",
+ "94 siÄ™ \n",
+ "95 zaczyna \n",
+ "96 za \n",
+ "97 siekierki \n",
+ "98 sanktuarium \n",
+ "99 no \n",
+ "100 właśnie \n",
+ "101 przed \n",
+ "102 tym \n",
+ "103 przed \n",
+ "104 tym \n",
+ "105 przystanek \n",
+ "106 o \n",
+ "107 której \n",
+ "108 jest \n",
+ "109 \n",
+ "110 \n",
+ "111 143 \n",
+ "112 najbliższy \n",
+ "113 \n",
+ "114 \n",
+ "115 \n",
+ "116 wtedy \n",
+ "117 przystanek \n",
+ "118 małe \n",
+ "119 siekierki \n",
+ "120 ale \n",
+ "121 to \n",
+ "122 nie \n",
+ "123 \n",
+ "124 \n",
+ "125 \n",
+ "126 \n",
+ "127 \n",
+ "128 \n",
+ "129 jest \n",
+ "130 dokonać \n",
+ "131 panoramy \n",
+ "132 dobrze \n",
+ "133 najbliższy \n",
+ "134 już \n",
+ "135 chwileczkÄ™ \n",
+ "136 czternasta \n",
+ "137 \n",
+ "138 46 \n",
+ "139 piętnasta \n",
+ "140 \n",
+ "141 0 \n",
+ "142 1 \n",
+ "143 aha \n",
+ "144 dobrze \n",
+ "145 dziękuję \n",
+ "146 \n",
+ "147 \n",
+ "148 do \n",
+ "149 widzenia "
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "\n"
+ ]
+ },
+ {
+ "data": {
+ "text/html": [
+ "<div>\n",
+ "<style scoped>\n",
+ " .dataframe tbody tr th:only-of-type {\n",
+ " vertical-align: middle;\n",
+ " }\n",
+ "\n",
+ " .dataframe tbody tr th {\n",
+ " vertical-align: top;\n",
+ " }\n",
+ "\n",
+ " .dataframe thead th {\n",
+ " text-align: right;\n",
+ " }\n",
+ "</style>\n",
+ "<table border=\"1\" class=\"dataframe\">\n",
+ " <thead>\n",
+ " <tr style=\"text-align: right;\">\n",
+ " <th></th>\n",
+ " <th>step_type</th>\n",
+ " <th>reference_word_text</th>\n",
+ " <th>hypothesis_word_text</th>\n",
" </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
" <tr>\n",
- " <th>154</th>\n",
+ " <th>0</th>\n",
+ " <td>DELETION</td>\n",
+ " <td>xxx</td>\n",
+ " <td></td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>1</th>\n",
" <td>CORRECT</td>\n",
- " <td>PART</td>\n",
- " <td>już</td>\n",
- " <td>PART</td>\n",
- " <td>już</td>\n",
+ " <td>dzień</td>\n",
+ " <td>dzień</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>155</th>\n",
+ " <th>2</th>\n",
" <td>CORRECT</td>\n",
- " <td>AUX</td>\n",
- " <td>jest</td>\n",
- " <td>AUX</td>\n",
- " <td>jest</td>\n",
+ " <td>dobry</td>\n",
+ " <td>dobry</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>156</th>\n",
+ " <th>3</th>\n",
" <td>CORRECT</td>\n",
- " <td>NOUN</td>\n",
- " <td>dzielnica</td>\n",
- " <td>NOUN</td>\n",
- " <td>dzielnica</td>\n",
+ " <td>dzień</td>\n",
+ " <td>dzień</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>157</th>\n",
+ " <th>4</th>\n",
" <td>CORRECT</td>\n",
- " <td>AUX</td>\n",
- " <td>to</td>\n",
- " <td>AUX</td>\n",
- " <td>to</td>\n",
+ " <td>dobry</td>\n",
+ " <td>dobry</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>158</th>\n",
+ " <th>5</th>\n",
" <td>CORRECT</td>\n",
- " <td>DET</td>\n",
- " <td>ta</td>\n",
- " <td>DET</td>\n",
- " <td>ta</td>\n",
+ " <td>proszÄ™</td>\n",
+ " <td>proszÄ™</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>159</th>\n",
+ " <th>6</th>\n",
" <td>CORRECT</td>\n",
- " <td>AUX</td>\n",
- " <td>jest</td>\n",
- " <td>AUX</td>\n",
- " <td>jest</td>\n",
+ " <td>pana</td>\n",
+ " <td>pana</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>160</th>\n",
+ " <th>7</th>\n",
" <td>CORRECT</td>\n",
- " <td>ADP</td>\n",
- " <td>przy</td>\n",
- " <td>ADP</td>\n",
- " <td>przy</td>\n",
+ " <td>ja</td>\n",
+ " <td>ja</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>161</th>\n",
+ " <th>8</th>\n",
" <td>CORRECT</td>\n",
- " <td>NOUN</td>\n",
- " <td>ulica</td>\n",
- " <td>NOUN</td>\n",
- " <td>ulica</td>\n",
+ " <td>mam</td>\n",
+ " <td>mam</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>162</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>PROPN</td>\n",
- " <td>Gagarina</td>\n",
- " <td>ADJ</td>\n",
- " <td>gagarina</td>\n",
+ " <th>9</th>\n",
+ " <td>INSERTION</td>\n",
+ " <td></td>\n",
+ " <td>pytanie</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>163</th>\n",
+ " <th>10</th>\n",
" <td>CORRECT</td>\n",
- " <td>CCONJ</td>\n",
- " <td>a</td>\n",
- " <td>CCONJ</td>\n",
- " <td>a</td>\n",
+ " <td>o</td>\n",
+ " <td>o</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>164</th>\n",
+ " <th>11</th>\n",
" <td>CORRECT</td>\n",
- " <td>ADP</td>\n",
- " <td>przy</td>\n",
- " <td>ADP</td>\n",
- " <td>przy</td>\n",
+ " <td>której</td>\n",
+ " <td>której</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>165</th>\n",
+ " <th>12</th>\n",
" <td>CORRECT</td>\n",
- " <td>NOUN</td>\n",
- " <td>ulicy</td>\n",
- " <td>NOUN</td>\n",
- " <td>ulicy</td>\n",
+ " <td>będzie</td>\n",
+ " <td>będzie</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>166</th>\n",
- " <td>CORRECT</td>\n",
- " <td>PROPN</td>\n",
- " <td>Gagarina</td>\n",
- " <td>PROPN</td>\n",
- " <td>gagarina</td>\n",
+ " <th>13</th>\n",
+ " <td>DELETION</td>\n",
+ " <td>sto</td>\n",
+ " <td></td>\n",
" </tr>\n",
" <tr>\n",
- " <th>167</th>\n",
- " <td>CORRECT</td>\n",
- " <td>CCONJ</td>\n",
- " <td>czyli</td>\n",
- " <td>CCONJ</td>\n",
- " <td>czyli</td>\n",
+ " <th>14</th>\n",
+ " <td>DELETION</td>\n",
+ " <td>czterdzieści</td>\n",
+ " <td></td>\n",
" </tr>\n",
" <tr>\n",
- " <th>168</th>\n",
+ " <th>15</th>\n",
+ " <td>SUBSTITUTION</td>\n",
+ " <td>trzy</td>\n",
+ " <td>143</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>16</th>\n",
" <td>CORRECT</td>\n",
- " <td>PRON</td>\n",
- " <td>to</td>\n",
- " <td>PRON</td>\n",
- " <td>to</td>\n",
+ " <td>będzie</td>\n",
+ " <td>będzie</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>169</th>\n",
+ " <th>17</th>\n",
" <td>CORRECT</td>\n",
- " <td>AUX</td>\n",
- " <td>jest</td>\n",
- " <td>AUX</td>\n",
- " <td>jest</td>\n",
+ " <td>najbliższy</td>\n",
+ " <td>najbliższy</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>170</th>\n",
+ " <th>18</th>\n",
" <td>CORRECT</td>\n",
- " <td>ADV</td>\n",
- " <td>tam</td>\n",
- " <td>ADV</td>\n",
- " <td>tam</td>\n",
+ " <td>z</td>\n",
+ " <td>z</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>171</th>\n",
+ " <th>19</th>\n",
+ " <td>INSERTION</td>\n",
+ " <td></td>\n",
+ " <td>alei</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>20</th>\n",
+ " <td>SUBSTITUTION</td>\n",
+ " <td>Alei</td>\n",
+ " <td>witosa</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>21</th>\n",
+ " <td>SUBSTITUTION</td>\n",
+ " <td>Alei</td>\n",
+ " <td>alei</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>22</th>\n",
+ " <td>SUBSTITUTION</td>\n",
+ " <td>Witosa</td>\n",
+ " <td>witosa</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>23</th>\n",
" <td>CORRECT</td>\n",
- " <td>NOUN</td>\n",
- " <td>Mokotów</td>\n",
- " <td>NOUN</td>\n",
- " <td>mokotów</td>\n",
+ " <td>w</td>\n",
+ " <td>w</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>172</th>\n",
+ " <th>24</th>\n",
" <td>CORRECT</td>\n",
- " <td>ADP</td>\n",
- " <td>po</td>\n",
- " <td>ADP</td>\n",
- " <td>po</td>\n",
+ " <td>stronÄ™</td>\n",
+ " <td>stronÄ™</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>173</th>\n",
+ " <th>25</th>\n",
+ " <td>DELETION</td>\n",
+ " <td>Gocławia</td>\n",
+ " <td></td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>26</th>\n",
+ " <td>DELETION</td>\n",
+ " <td>z</td>\n",
+ " <td></td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>27</th>\n",
+ " <td>SUBSTITUTION</td>\n",
+ " <td>tego</td>\n",
+ " <td>gocławia</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>28</th>\n",
" <td>CORRECT</td>\n",
- " <td>ADJ</td>\n",
- " <td>prostu</td>\n",
- " <td>ADJ</td>\n",
- " <td>prostu</td>\n",
+ " <td>przystanku</td>\n",
+ " <td>przystanku</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>174</th>\n",
+ " <th>29</th>\n",
+ " <td>DELETION</td>\n",
+ " <td>vis</td>\n",
+ " <td></td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>30</th>\n",
+ " <td>DELETION</td>\n",
+ " <td>-</td>\n",
+ " <td></td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>31</th>\n",
+ " <td>DELETION</td>\n",
+ " <td>a</td>\n",
+ " <td></td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>32</th>\n",
+ " <td>DELETION</td>\n",
+ " <td>-</td>\n",
+ " <td></td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>33</th>\n",
+ " <td>SUBSTITUTION</td>\n",
+ " <td>vis</td>\n",
+ " <td>widzowi</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>34</th>\n",
+ " <td>SUBSTITUTION</td>\n",
+ " <td>ZUSu</td>\n",
+ " <td>zusu</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>35</th>\n",
" <td>CORRECT</td>\n",
- " <td>ADV</td>\n",
" <td>tak</td>\n",
- " <td>ADV</td>\n",
" <td>tak</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>175</th>\n",
+ " <th>36</th>\n",
" <td>DELETION</td>\n",
- " <td>PUNCT</td>\n",
" <td>?</td>\n",
" <td></td>\n",
- " <td></td>\n",
" </tr>\n",
" <tr>\n",
- " <th>176</th>\n",
+ " <th>37</th>\n",
" <td>CORRECT</td>\n",
- " <td>ADV</td>\n",
- " <td>tak</td>\n",
- " <td>ADV</td>\n",
- " <td>tak</td>\n",
+ " <td>no</td>\n",
+ " <td>no</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>177</th>\n",
+ " <th>38</th>\n",
" <td>CORRECT</td>\n",
- " <td>NOUN</td>\n",
- " <td>Siekierki</td>\n",
- " <td>NOUN</td>\n",
- " <td>siekierki</td>\n",
+ " <td>nie</td>\n",
+ " <td>nie</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>178</th>\n",
+ " <th>39</th>\n",
" <td>CORRECT</td>\n",
- " <td>PROPN</td>\n",
- " <td>Mokotów</td>\n",
- " <td>PROPN</td>\n",
- " <td>mokot</td>\n",
+ " <td>nie</td>\n",
+ " <td>nie</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>179</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>CCONJ</td>\n",
+ " <th>40</th>\n",
+ " <td>CORRECT</td>\n",
+ " <td>tam</td>\n",
+ " <td>tam</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>41</th>\n",
+ " <td>DELETION</td>\n",
+ " <td>vis</td>\n",
+ " <td></td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>42</th>\n",
+ " <td>DELETION</td>\n",
+ " <td>-</td>\n",
+ " <td></td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>43</th>\n",
+ " <td>DELETION</td>\n",
" <td>a</td>\n",
- " <td>NOUN</td>\n",
- " <td>siekierki</td>\n",
+ " <td></td>\n",
" </tr>\n",
" <tr>\n",
- " <th>180</th>\n",
+ " <th>44</th>\n",
+ " <td>DELETION</td>\n",
+ " <td>-</td>\n",
+ " <td></td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>45</th>\n",
" <td>SUBSTITUTION</td>\n",
- " <td>NOUN</td>\n",
- " <td>Siekierki</td>\n",
- " <td>VERB</td>\n",
- " <td>mokot</td>\n",
+ " <td>vis</td>\n",
+ " <td>widzowi</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>181</th>\n",
+ " <th>46</th>\n",
" <td>SUBSTITUTION</td>\n",
- " <td>PROPN</td>\n",
- " <td>Mokotów</td>\n",
- " <td>DET</td>\n",
- " <td>ów</td>\n",
+ " <td>Panoramy</td>\n",
+ " <td>panoramy</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>182</th>\n",
+ " <th>47</th>\n",
" <td>CORRECT</td>\n",
- " <td>CCONJ</td>\n",
- " <td>i</td>\n",
- " <td>CCONJ</td>\n",
- " <td>i</td>\n",
+ " <td>przez</td>\n",
+ " <td>przez</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>183</th>\n",
+ " <th>48</th>\n",
+ " <td>SUBSTITUTION</td>\n",
+ " <td>Siekierkowski</td>\n",
+ " <td>siekierkowski</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>49</th>\n",
" <td>CORRECT</td>\n",
- " <td>ADV</td>\n",
" <td>tam</td>\n",
- " <td>ADV</td>\n",
" <td>tam</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>184</th>\n",
+ " <th>50</th>\n",
" <td>CORRECT</td>\n",
- " <td>SCONJ</td>\n",
- " <td>jak</td>\n",
- " <td>SCONJ</td>\n",
- " <td>jak</td>\n",
+ " <td>w</td>\n",
+ " <td>w</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>185</th>\n",
+ " <th>51</th>\n",
" <td>CORRECT</td>\n",
- " <td>NOUN</td>\n",
- " <td>pani</td>\n",
- " <td>NOUN</td>\n",
- " <td>pani</td>\n",
+ " <td>stronÄ™</td>\n",
+ " <td>stronÄ™</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>186</th>\n",
+ " <th>52</th>\n",
+ " <td>SUBSTITUTION</td>\n",
+ " <td>Gocławia</td>\n",
+ " <td>gocławia</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>53</th>\n",
" <td>CORRECT</td>\n",
- " <td>VERB</td>\n",
- " <td>wysiÄ…dzie</td>\n",
- " <td>VERB</td>\n",
- " <td>wysiÄ…dzie</td>\n",
+ " <td>ale</td>\n",
+ " <td>ale</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>187</th>\n",
+ " <th>54</th>\n",
" <td>CORRECT</td>\n",
- " <td>DET</td>\n",
" <td>to</td>\n",
- " <td>DET</td>\n",
" <td>to</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>188</th>\n",
+ " <th>55</th>\n",
" <td>CORRECT</td>\n",
- " <td>NOUN</td>\n",
- " <td>trza</td>\n",
- " <td>NOUN</td>\n",
- " <td>trza</td>\n",
+ " <td>nie</td>\n",
+ " <td>nie</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>189</th>\n",
+ " <th>56</th>\n",
" <td>CORRECT</td>\n",
- " <td>VERB</td>\n",
- " <td>wejść</td>\n",
- " <td>VERB</td>\n",
- " <td>wejść</td>\n",
+ " <td>z</td>\n",
+ " <td>z</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>190</th>\n",
- " <td>DELETION</td>\n",
- " <td>ADP</td>\n",
- " <td>w</td>\n",
- " <td></td>\n",
- " <td></td>\n",
+ " <th>57</th>\n",
+ " <td>CORRECT</td>\n",
+ " <td>tego</td>\n",
+ " <td>tego</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>191</th>\n",
- " <td>DELETION</td>\n",
- " <td>NOUN</td>\n",
- " <td>lewo</td>\n",
- " <td></td>\n",
- " <td></td>\n",
+ " <th>58</th>\n",
+ " <td>CORRECT</td>\n",
+ " <td>przystanku</td>\n",
+ " <td>przystanku</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>192</th>\n",
+ " <th>59</th>\n",
" <td>DELETION</td>\n",
- " <td>ADP</td>\n",
- " <td>w</td>\n",
- " <td></td>\n",
+ " <td>Aleja</td>\n",
" <td></td>\n",
" </tr>\n",
" <tr>\n",
- " <th>193</th>\n",
+ " <th>60</th>\n",
+ " <td>SUBSTITUTION</td>\n",
+ " <td>Witosa</td>\n",
+ " <td>aleja</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>61</th>\n",
+ " <td>SUBSTITUTION</td>\n",
+ " <td>?</td>\n",
+ " <td>witosa</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>62</th>\n",
" <td>CORRECT</td>\n",
- " <td>NOUN</td>\n",
- " <td>ulicÄ™</td>\n",
- " <td>NOUN</td>\n",
- " <td>scenerii</td>\n",
+ " <td>no</td>\n",
+ " <td>no</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>194</th>\n",
- " <td>DELETION</td>\n",
- " <td>PROPN</td>\n",
- " <td>Nehru</td>\n",
- " <td></td>\n",
- " <td></td>\n",
+ " <th>63</th>\n",
+ " <td>CORRECT</td>\n",
+ " <td>to</td>\n",
+ " <td>to</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>195</th>\n",
+ " <th>64</th>\n",
" <td>CORRECT</td>\n",
- " <td>CCONJ</td>\n",
- " <td>i</td>\n",
- " <td>CCONJ</td>\n",
- " <td>i</td>\n",
+ " <td>jest</td>\n",
+ " <td>jest</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>196</th>\n",
+ " <th>65</th>\n",
" <td>CORRECT</td>\n",
- " <td>ADP</td>\n",
- " <td>od</td>\n",
- " <td>ADP</td>\n",
- " <td>od</td>\n",
+ " <td>czy</td>\n",
+ " <td>czy</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>197</th>\n",
+ " <th>66</th>\n",
" <td>SUBSTITUTION</td>\n",
- " <td>PROPN</td>\n",
- " <td>Nehru</td>\n",
- " <td>NOUN</td>\n",
- " <td>nehru</td>\n",
+ " <td>Bartoszka</td>\n",
+ " <td>bartoszka</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>198</th>\n",
+ " <th>67</th>\n",
" <td>CORRECT</td>\n",
- " <td>VERB</td>\n",
- " <td>odchodzi</td>\n",
- " <td>VERB</td>\n",
- " <td>odchodzi</td>\n",
+ " <td>na</td>\n",
+ " <td>na</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>199</th>\n",
+ " <th>68</th>\n",
" <td>CORRECT</td>\n",
- " <td>ADJ</td>\n",
- " <td>Zwierzyniecka</td>\n",
- " <td>ADJ</td>\n",
- " <td>zwierzyniecka</td>\n",
+ " <td>żądanie</td>\n",
+ " <td>żądanie</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>200</th>\n",
+ " <th>69</th>\n",
" <td>CORRECT</td>\n",
- " <td>ADP</td>\n",
- " <td>w</td>\n",
- " <td>ADP</td>\n",
- " <td>w</td>\n",
+ " <td>wie</td>\n",
+ " <td>wie</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>201</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>ADV</td>\n",
- " <td>lewo</td>\n",
- " <td>NOUN</td>\n",
- " <td>le</td>\n",
+ " <th>70</th>\n",
+ " <td>CORRECT</td>\n",
+ " <td>pan</td>\n",
+ " <td>pan</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>202</th>\n",
+ " <th>71</th>\n",
" <td>CORRECT</td>\n",
- " <td>ADP</td>\n",
- " <td>w</td>\n",
- " <td>ADP</td>\n",
- " <td>w</td>\n",
+ " <td>gdzie</td>\n",
+ " <td>gdzie</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>203</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>ADV</td>\n",
- " <td>lewo</td>\n",
- " <td>NOUN</td>\n",
- " <td>lewo</td>\n",
+ " <th>72</th>\n",
+ " <td>CORRECT</td>\n",
+ " <td>jest</td>\n",
+ " <td>jest</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>204</th>\n",
+ " <th>73</th>\n",
" <td>CORRECT</td>\n",
- " <td>CCONJ</td>\n",
- " <td>i</td>\n",
- " <td>CCONJ</td>\n",
- " <td>i</td>\n",
+ " <td>siÄ™</td>\n",
+ " <td>siÄ™</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>205</th>\n",
+ " <th>74</th>\n",
" <td>CORRECT</td>\n",
- " <td>NOUN</td>\n",
- " <td>ulica</td>\n",
- " <td>NOUN</td>\n",
- " <td>ulica</td>\n",
+ " <td>zaczyna</td>\n",
+ " <td>zaczyna</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>206</th>\n",
- " <td>DELETION</td>\n",
- " <td>PROPN</td>\n",
- " <td>Nehru</td>\n",
- " <td></td>\n",
- " <td></td>\n",
+ " <th>75</th>\n",
+ " <td>SUBSTITUTION</td>\n",
+ " <td>Most</td>\n",
+ " <td>most</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>207</th>\n",
+ " <th>76</th>\n",
" <td>SUBSTITUTION</td>\n",
- " <td>PUNCT</td>\n",
- " <td>?</td>\n",
- " <td>ADJ</td>\n",
- " <td>nehru</td>\n",
+ " <td>Siekierkowski</td>\n",
+ " <td>siekierkowski</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>208</th>\n",
+ " <th>77</th>\n",
" <td>CORRECT</td>\n",
- " <td>ADV</td>\n",
- " <td>tak</td>\n",
- " <td>ADV</td>\n",
- " <td>tak</td>\n",
+ " <td>tam</td>\n",
+ " <td>tam</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>209</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>PROPN</td>\n",
- " <td>Nehru</td>\n",
- " <td>VERB</td>\n",
- " <td>nehru</td>\n",
+ " <th>78</th>\n",
+ " <td>CORRECT</td>\n",
+ " <td>w</td>\n",
+ " <td>w</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>210</th>\n",
+ " <th>79</th>\n",
" <td>CORRECT</td>\n",
- " <td>ADV</td>\n",
- " <td>dobrze</td>\n",
- " <td>ADV</td>\n",
- " <td>dobrze</td>\n",
+ " <td>stronÄ™</td>\n",
+ " <td>stronÄ™</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>211</th>\n",
+ " <th>80</th>\n",
+ " <td>DELETION</td>\n",
+ " <td>Gocławia</td>\n",
+ " <td></td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>81</th>\n",
+ " <td>DELETION</td>\n",
+ " <td>gdzie</td>\n",
+ " <td></td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>82</th>\n",
+ " <td>SUBSTITUTION</td>\n",
+ " <td>ma</td>\n",
+ " <td>wrocław</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>83</th>\n",
" <td>CORRECT</td>\n",
- " <td>VERB</td>\n",
- " <td>dziękuję</td>\n",
- " <td>VERB</td>\n",
- " <td>dziękuję</td>\n",
+ " <td>on</td>\n",
+ " <td>on</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>212</th>\n",
+ " <th>84</th>\n",
" <td>CORRECT</td>\n",
- " <td>NOUN</td>\n",
- " <td>panu</td>\n",
- " <td>NOUN</td>\n",
- " <td>panu</td>\n",
+ " <td>przystanek</td>\n",
+ " <td>przystanek</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>213</th>\n",
+ " <th>85</th>\n",
" <td>CORRECT</td>\n",
- " <td>ADV</td>\n",
- " <td>bardzo</td>\n",
- " <td>ADV</td>\n",
- " <td>bardzo</td>\n",
+ " <td>pierwszy</td>\n",
+ " <td>pierwszy</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>214</th>\n",
+ " <th>86</th>\n",
" <td>DELETION</td>\n",
- " <td>VERB</td>\n",
- " <td>proszÄ™</td>\n",
+ " <td>sto</td>\n",
" <td></td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>87</th>\n",
+ " <td>DELETION</td>\n",
+ " <td>czterdzieści</td>\n",
" <td></td>\n",
" </tr>\n",
" <tr>\n",
- " <th>215</th>\n",
+ " <th>88</th>\n",
+ " <td>SUBSTITUTION</td>\n",
+ " <td>trzy</td>\n",
+ " <td>143</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>89</th>\n",
" <td>CORRECT</td>\n",
- " <td>ADP</td>\n",
- " <td>do</td>\n",
- " <td>ADP</td>\n",
- " <td>do</td>\n",
+ " <td>znaczy</td>\n",
+ " <td>znaczy</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>216</th>\n",
+ " <th>90</th>\n",
" <td>CORRECT</td>\n",
- " <td>NOUN</td>\n",
- " <td>widzenia</td>\n",
- " <td>NOUN</td>\n",
- " <td>widzenia</td>\n",
+ " <td>tak</td>\n",
+ " <td>tak</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>217</th>\n",
+ " <th>91</th>\n",
+ " <td>CORRECT</td>\n",
+ " <td>naprawdÄ™</td>\n",
+ " <td>naprawdÄ™</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>92</th>\n",
" <td>SUBSTITUTION</td>\n",
- " <td>ADP</td>\n",
- " <td>do</td>\n",
- " <td>DET</td>\n",
- " <td>to</td>\n",
+ " <td>Most</td>\n",
+ " <td>most</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>218</th>\n",
+ " <th>93</th>\n",
" <td>SUBSTITUTION</td>\n",
- " <td>NOUN</td>\n",
- " <td>widzenia</td>\n",
- " <td>PRON</td>\n",
- " <td>wszystko</td>\n",
+ " <td>Siekierkowski</td>\n",
+ " <td>siekierkowski</td>\n",
" </tr>\n",
- " </tbody>\n",
- "</table>\n",
- "</div>"
+ " <tr>\n",
+ " <th>94</th>\n",
+ " <td>CORRECT</td>\n",
+ " <td>to</td>\n",
+ " <td>to</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>95</th>\n",
+ " <td>CORRECT</td>\n",
+ " <td>siÄ™</td>\n",
+ " <td>siÄ™</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>96</th>\n",
+ " <td>CORRECT</td>\n",
+ " <td>zaczyna</td>\n",
+ " <td>zaczyna</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>97</th>\n",
+ " <td>CORRECT</td>\n",
+ " <td>za</td>\n",
+ " <td>za</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>98</th>\n",
+ " <td>SUBSTITUTION</td>\n",
+ " <td>Siekierki</td>\n",
+ " <td>siekierki</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>99</th>\n",
+ " <td>SUBSTITUTION</td>\n",
+ " <td>Sanktuarium</td>\n",
+ " <td>sanktuarium</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>100</th>\n",
+ " <td>CORRECT</td>\n",
+ " <td>no</td>\n",
+ " <td>no</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>101</th>\n",
+ " <td>CORRECT</td>\n",
+ " <td>właśnie</td>\n",
+ " <td>właśnie</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>102</th>\n",
+ " <td>CORRECT</td>\n",
+ " <td>przed</td>\n",
+ " <td>przed</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>103</th>\n",
+ " <td>CORRECT</td>\n",
+ " <td>tym</td>\n",
+ " <td>tym</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>104</th>\n",
+ " <td>CORRECT</td>\n",
+ " <td>przed</td>\n",
+ " <td>przed</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>105</th>\n",
+ " <td>CORRECT</td>\n",
+ " <td>tym</td>\n",
+ " <td>tym</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>106</th>\n",
+ " <td>CORRECT</td>\n",
+ " <td>przystanek</td>\n",
+ " <td>przystanek</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>107</th>\n",
+ " <td>CORRECT</td>\n",
+ " <td>o</td>\n",
+ " <td>o</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>108</th>\n",
+ " <td>CORRECT</td>\n",
+ " <td>której</td>\n",
+ " <td>której</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>109</th>\n",
+ " <td>CORRECT</td>\n",
+ " <td>jest</td>\n",
+ " <td>jest</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>110</th>\n",
+ " <td>DELETION</td>\n",
+ " <td>sto</td>\n",
+ " <td></td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>111</th>\n",
+ " <td>DELETION</td>\n",
+ " <td>czterdzieści</td>\n",
+ " <td></td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>112</th>\n",
+ " <td>SUBSTITUTION</td>\n",
+ " <td>trzy</td>\n",
+ " <td>143</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>113</th>\n",
+ " <td>CORRECT</td>\n",
+ " <td>najbliższy</td>\n",
+ " <td>najbliższy</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>114</th>\n",
+ " <td>DELETION</td>\n",
+ " <td>aha</td>\n",
+ " <td></td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>115</th>\n",
+ " <td>DELETION</td>\n",
+ " <td>czyli</td>\n",
+ " <td></td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>116</th>\n",
+ " <td>DELETION</td>\n",
+ " <td>to</td>\n",
+ " <td></td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>117</th>\n",
+ " <td>CORRECT</td>\n",
+ " <td>wtedy</td>\n",
+ " <td>wtedy</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>118</th>\n",
+ " <td>CORRECT</td>\n",
+ " <td>przystanek</td>\n",
+ " <td>przystanek</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>119</th>\n",
+ " <td>SUBSTITUTION</td>\n",
+ " <td>Małe</td>\n",
+ " <td>małe</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>120</th>\n",
+ " <td>SUBSTITUTION</td>\n",
+ " <td>Siekierki</td>\n",
+ " <td>siekierki</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>121</th>\n",
+ " <td>CORRECT</td>\n",
+ " <td>ale</td>\n",
+ " <td>ale</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>122</th>\n",
+ " <td>CORRECT</td>\n",
+ " <td>to</td>\n",
+ " <td>to</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>123</th>\n",
+ " <td>CORRECT</td>\n",
+ " <td>nie</td>\n",
+ " <td>nie</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>124</th>\n",
+ " <td>CORRECT</td>\n",
+ " <td>jest</td>\n",
+ " <td>jest</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>125</th>\n",
+ " <td>DELETION</td>\n",
+ " <td>tak</td>\n",
+ " <td></td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>126</th>\n",
+ " <td>DELETION</td>\n",
+ " <td>tak</td>\n",
+ " <td></td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>127</th>\n",
+ " <td>DELETION</td>\n",
+ " <td>tak</td>\n",
+ " <td></td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>128</th>\n",
+ " <td>DELETION</td>\n",
+ " <td>tak</td>\n",
+ " <td></td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>129</th>\n",
+ " <td>DELETION</td>\n",
+ " <td>na</td>\n",
+ " <td></td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>130</th>\n",
+ " <td>DELETION</td>\n",
+ " <td>wysokości</td>\n",
+ " <td></td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>131</th>\n",
+ " <td>SUBSTITUTION</td>\n",
+ " <td>Panoramy</td>\n",
+ " <td>dokonać</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>132</th>\n",
+ " <td>SUBSTITUTION</td>\n",
+ " <td>aha</td>\n",
+ " <td>panoramy</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>133</th>\n",
+ " <td>CORRECT</td>\n",
+ " <td>dobrze</td>\n",
+ " <td>dobrze</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>134</th>\n",
+ " <td>CORRECT</td>\n",
+ " <td>najbliższy</td>\n",
+ " <td>najbliższy</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>135</th>\n",
+ " <td>CORRECT</td>\n",
+ " <td>już</td>\n",
+ " <td>już</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>136</th>\n",
+ " <td>CORRECT</td>\n",
+ " <td>chwileczkÄ™</td>\n",
+ " <td>chwileczkÄ™</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>137</th>\n",
+ " <td>CORRECT</td>\n",
+ " <td>czternasta</td>\n",
+ " <td>czternasta</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>138</th>\n",
+ " <td>DELETION</td>\n",
+ " <td>czterdzieści</td>\n",
+ " <td></td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>139</th>\n",
+ " <td>SUBSTITUTION</td>\n",
+ " <td>sześć</td>\n",
+ " <td>46</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>140</th>\n",
+ " <td>CORRECT</td>\n",
+ " <td>piętnasta</td>\n",
+ " <td>piętnasta</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>141</th>\n",
+ " <td>SUBSTITUTION</td>\n",
+ " <td>zero</td>\n",
+ " <td>0</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>142</th>\n",
+ " <td>SUBSTITUTION</td>\n",
+ " <td>jeden</td>\n",
+ " <td>1</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>143</th>\n",
+ " <td>CORRECT</td>\n",
+ " <td>aha</td>\n",
+ " <td>aha</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>144</th>\n",
+ " <td>DELETION</td>\n",
+ " <td>no</td>\n",
+ " <td></td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>145</th>\n",
+ " <td>CORRECT</td>\n",
+ " <td>dobrze</td>\n",
+ " <td>dobrze</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>146</th>\n",
+ " <td>CORRECT</td>\n",
+ " <td>dziękuję</td>\n",
+ " <td>dziękuję</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>147</th>\n",
+ " <td>DELETION</td>\n",
+ " <td>do</td>\n",
+ " <td></td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>148</th>\n",
+ " <td>DELETION</td>\n",
+ " <td>widzenia</td>\n",
+ " <td></td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>149</th>\n",
+ " <td>CORRECT</td>\n",
+ " <td>do</td>\n",
+ " <td>do</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>150</th>\n",
+ " <td>CORRECT</td>\n",
+ " <td>widzenia</td>\n",
+ " <td>widzenia</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "</div>"
],
"text/plain": [
- " step_type reference_word_pos reference_word_text hypothesis_word_pos \\\n",
- "0 DELETION PRON xxx \n",
- "1 CORRECT NOUN dzień NOUN \n",
- "2 CORRECT ADJ dobry ADJ \n",
- "3 CORRECT NOUN dzień NOUN \n",
- "4 CORRECT ADJ dobry ADJ \n",
- "5 CORRECT VERB proszÄ™ VERB \n",
- "6 CORRECT NOUN pana NOUN \n",
- "7 CORRECT PRON ja PRON \n",
- "8 CORRECT VERB chciałam VERB \n",
- "9 CORRECT PRON siÄ™ PRON \n",
- "10 CORRECT VERB dowiedzieć VERB \n",
- "11 CORRECT SCONJ bo SCONJ \n",
- "12 CORRECT PART nie PART \n",
- "13 CORRECT ADV bardzo ADV \n",
- "14 CORRECT VERB wiem VERB \n",
- "15 CORRECT ADV gdzie ADV \n",
- "16 CORRECT VERB znajduje VERB \n",
- "17 CORRECT PRON siÄ™ PRON \n",
- "18 CORRECT NOUN ulica NOUN \n",
- "19 CORRECT ADJ Zwierzyniecka ADJ \n",
- "20 CORRECT CCONJ i CCONJ \n",
- "21 CORRECT ADV jak ADV \n",
- "22 CORRECT VERB dojechać VERB \n",
- "23 DELETION ADP z \n",
- "24 DELETION PROPN Bródna \n",
- "25 CORRECT ADP na ADP \n",
- "26 CORRECT NOUN przykład NOUN \n",
- "27 DELETION PUNCT ? \n",
- "28 CORRECT ADP na ADP \n",
- "29 CORRECT PROPN ZwierzynieckÄ… PROPN \n",
- "30 CORRECT ADP na ADP \n",
- "31 CORRECT PROPN ZwierzynieckÄ… PROPN \n",
- "32 SUBSTITUTION CCONJ a PRON \n",
- "33 CORRECT ADP z ADP \n",
- "34 SUBSTITUTION PROPN Bródna NOUN \n",
- "35 CORRECT ADP z ADP \n",
- "36 CORRECT DET którego DET \n",
- "37 CORRECT NOUN miejsca NOUN \n",
- "38 DELETION PUNCT ? \n",
- "39 CORRECT ADP z ADP \n",
- "40 SUBSTITUTION PROPN Bródna NOUN \n",
- "41 CORRECT AUX to AUX \n",
- "42 CORRECT AUX jest AUX \n",
- "43 CORRECT NOUN ulica NOUN \n",
- "44 SUBSTITUTION PROPN Wyszogrodzka ADJ \n",
- "45 CORRECT ADV tu ADV \n",
- "46 CORRECT ADP przy ADP \n",
- "47 SUBSTITUTION PROPN Rembielińskiej ADJ \n",
- "48 CORRECT CCONJ czyli CCONJ \n",
- "49 CORRECT ADP przy ADP \n",
- "50 CORRECT NOUN tramwajach NOUN \n",
- "51 DELETION ADV tak \n",
- "52 DELETION PUNCT ? \n",
- "53 CORRECT ADP przy ADP \n",
- "54 CORRECT NOUN tramwajach NOUN \n",
- "55 CORRECT ADV tak ADV \n",
- "56 DELETION VERB może \n",
- "57 DELETION NOUN pani \n",
- "58 SUBSTITUTION VERB poczeka PART \n",
- "59 CORRECT VERB sprawdzÄ™ VERB \n",
- "60 CORRECT ADV dobrze ADV \n",
- "61 CORRECT ADV dobrze ADV \n",
- "62 DELETION NOUN pani \n",
- "63 DELETION PRON sobie \n",
- "64 CORRECT VERB podjedzie VERB \n",
- "65 CORRECT NOUN tramwajem NOUN \n",
- "66 CORRECT ADP do ADP \n",
- "67 CORRECT NOUN Ronda NOUN \n",
- "68 SUBSTITUTION PROPN Żaba NOUN \n",
- "69 CORRECT ADV tak ADV \n",
- "70 CORRECT ADP od ADP \n",
- "71 CORRECT NOUN Ronda NOUN \n",
- "72 SUBSTITUTION PROPN Żaba NOUN \n",
- "73 CORRECT PART już PART \n",
- "74 DELETION NUM sto \n",
- "75 DELETION NUM sześćdziesiąt \n",
- "76 DELETION NUM dwa \n",
- "77 DELETION AUX jest \n",
- "78 CORRECT NUM sto NUM \n",
- "79 SUBSTITUTION NUM sześćdziesiąt VERB \n",
- "80 SUBSTITUTION NUM dwa X \n",
- "81 CORRECT ADV tak ADV \n",
- "82 CORRECT CCONJ i CCONJ \n",
- "83 DELETION NUM sto \n",
- "84 DELETION NUM sześćdziesiąt \n",
- "85 CORRECT NUM dwa NUM \n",
- "86 CORRECT ADV tam ADV \n",
- "87 CORRECT VERB dojadÄ™ VERB \n",
- "88 CORRECT ADP do ADP \n",
- "89 CORRECT DET tej DET \n",
- "90 CORRECT NOUN ulicy NOUN \n",
- "91 CORRECT ADV tak ADV \n",
- "92 CORRECT VERB może VERB \n",
- "93 CORRECT NOUN pani NOUN \n",
- "94 CORRECT VERB wysiąść VERB \n",
- "95 DELETION ADP na \n",
- "96 CORRECT NOUN przystanku NOUN \n",
- "97 CORRECT PROPN Bartycka PROPN \n",
- "98 CORRECT CCONJ albo CCONJ \n",
- "99 CORRECT PROPN Sielce PROPN \n",
- "100 CORRECT PROPN Bartycka PROPN \n",
- "101 CORRECT CCONJ albo CCONJ \n",
- "102 DELETION PUNCT ? \n",
- "103 SUBSTITUTION PROPN Sielce NOUN \n",
- "104 CORRECT PROPN Sielce PROPN \n",
- "105 CORRECT ADV tak ADV \n",
- "106 DELETION PUNCT ? \n",
- "107 CORRECT ADV tak ADV \n",
- "108 CORRECT X aha X \n",
- "109 CORRECT CCONJ i CCONJ \n",
- "110 CORRECT ADV tam ADV \n",
- "111 CORRECT ADP w ADP \n",
- "112 CORRECT NOUN pobliżu NOUN \n",
- "113 CORRECT AUX jest AUX \n",
- "114 CORRECT DET ta DET \n",
- "115 CORRECT NOUN ulica NOUN \n",
- "116 DELETION ADV tak \n",
- "117 SUBSTITUTION PUNCT ? ADJ \n",
- "118 SUBSTITUTION CCONJ a VERB \n",
- "119 CORRECT NOUN Zwierzyniecka NOUN \n",
- "120 CORRECT ADJ wysoki ADJ \n",
- "121 CORRECT NOUN numer NOUN \n",
- "122 DELETION VERB ma \n",
- "123 SUBSTITUTION NOUN pani ADJ \n",
- "124 SUBSTITUTION PUNCT ? DET \n",
- "125 SUBSTITUTION PROPN Zwierzyniecka X \n",
- "126 SUBSTITUTION ADV zaraz CCONJ \n",
- "127 CORRECT NOUN momencik NOUN \n",
- "128 DELETION NUM osiem \n",
- "129 DELETION CCONJ A \n",
- "130 SUBSTITUTION PROPN Zwierzyniecka PRON \n",
- "131 CORRECT AUX to AUX \n",
- "132 DELETION PRON to \n",
- "133 CORRECT ADP przy ADP \n",
- "134 SUBSTITUTION PROPN Sielce NOUN \n",
- "135 CORRECT NOUN trza NOUN \n",
- "136 CORRECT VERB wysiąść VERB \n",
- "137 CORRECT ADP przy ADP \n",
- "138 CORRECT PROPN Sielce PROPN \n",
- "139 CORRECT ADV tak ADV \n",
- "140 SUBSTITUTION PUNCT ? ADV \n",
- "141 CORRECT ADV tak ADV \n",
- "142 CORRECT NOUN przystanek NOUN \n",
- "143 DELETION PROPN Sielce \n",
- "144 CORRECT X aha X \n",
- "145 DELETION ADV tak \n",
- "146 CORRECT PART no PART \n",
- "147 CORRECT ADV dobrze ADV \n",
- "148 CORRECT CCONJ a CCONJ \n",
- "149 CORRECT PROPN Sielce PROPN \n",
- "150 DELETION PRON to \n",
- "151 DELETION VERB znaczy \n",
- "152 CORRECT DET jaka DET \n",
- "153 CORRECT AUX to AUX \n",
- "154 CORRECT PART już PART \n",
- "155 CORRECT AUX jest AUX \n",
- "156 CORRECT NOUN dzielnica NOUN \n",
- "157 CORRECT AUX to AUX \n",
- "158 CORRECT DET ta DET \n",
- "159 CORRECT AUX jest AUX \n",
- "160 CORRECT ADP przy ADP \n",
- "161 CORRECT NOUN ulica NOUN \n",
- "162 SUBSTITUTION PROPN Gagarina ADJ \n",
- "163 CORRECT CCONJ a CCONJ \n",
- "164 CORRECT ADP przy ADP \n",
- "165 CORRECT NOUN ulicy NOUN \n",
- "166 CORRECT PROPN Gagarina PROPN \n",
- "167 CORRECT CCONJ czyli CCONJ \n",
- "168 CORRECT PRON to PRON \n",
- "169 CORRECT AUX jest AUX \n",
- "170 CORRECT ADV tam ADV \n",
- "171 CORRECT NOUN Mokotów NOUN \n",
- "172 CORRECT ADP po ADP \n",
- "173 CORRECT ADJ prostu ADJ \n",
- "174 CORRECT ADV tak ADV \n",
- "175 DELETION PUNCT ? \n",
- "176 CORRECT ADV tak ADV \n",
- "177 CORRECT NOUN Siekierki NOUN \n",
- "178 CORRECT PROPN Mokotów PROPN \n",
- "179 SUBSTITUTION CCONJ a NOUN \n",
- "180 SUBSTITUTION NOUN Siekierki VERB \n",
- "181 SUBSTITUTION PROPN Mokotów DET \n",
- "182 CORRECT CCONJ i CCONJ \n",
- "183 CORRECT ADV tam ADV \n",
- "184 CORRECT SCONJ jak SCONJ \n",
- "185 CORRECT NOUN pani NOUN \n",
- "186 CORRECT VERB wysiÄ…dzie VERB \n",
- "187 CORRECT DET to DET \n",
- "188 CORRECT NOUN trza NOUN \n",
- "189 CORRECT VERB wejść VERB \n",
- "190 DELETION ADP w \n",
- "191 DELETION NOUN lewo \n",
- "192 DELETION ADP w \n",
- "193 CORRECT NOUN ulicÄ™ NOUN \n",
- "194 DELETION PROPN Nehru \n",
- "195 CORRECT CCONJ i CCONJ \n",
- "196 CORRECT ADP od ADP \n",
- "197 SUBSTITUTION PROPN Nehru NOUN \n",
- "198 CORRECT VERB odchodzi VERB \n",
- "199 CORRECT ADJ Zwierzyniecka ADJ \n",
- "200 CORRECT ADP w ADP \n",
- "201 SUBSTITUTION ADV lewo NOUN \n",
- "202 CORRECT ADP w ADP \n",
- "203 SUBSTITUTION ADV lewo NOUN \n",
- "204 CORRECT CCONJ i CCONJ \n",
- "205 CORRECT NOUN ulica NOUN \n",
- "206 DELETION PROPN Nehru \n",
- "207 SUBSTITUTION PUNCT ? ADJ \n",
- "208 CORRECT ADV tak ADV \n",
- "209 SUBSTITUTION PROPN Nehru VERB \n",
- "210 CORRECT ADV dobrze ADV \n",
- "211 CORRECT VERB dziękuję VERB \n",
- "212 CORRECT NOUN panu NOUN \n",
- "213 CORRECT ADV bardzo ADV \n",
- "214 DELETION VERB proszÄ™ \n",
- "215 CORRECT ADP do ADP \n",
- "216 CORRECT NOUN widzenia NOUN \n",
- "217 SUBSTITUTION ADP do DET \n",
- "218 SUBSTITUTION NOUN widzenia PRON \n",
- "\n",
- " hypothesis_word_text \n",
- "0 \n",
- "1 dzień \n",
- "2 dobry \n",
- "3 dzień \n",
- "4 dobry \n",
- "5 proszÄ™ \n",
- "6 pana \n",
- "7 ja \n",
- "8 chciałam \n",
- "9 siÄ™ \n",
- "10 dowiedzieć \n",
- "11 bo \n",
- "12 nie \n",
- "13 bardzo \n",
- "14 wiem \n",
- "15 gdzie \n",
- "16 znajduje \n",
- "17 siÄ™ \n",
- "18 ulica \n",
- "19 zwierzyniecka \n",
- "20 i \n",
- "21 jak \n",
- "22 dojechać \n",
- "23 \n",
- "24 \n",
- "25 z \n",
- "26 bródna \n",
- "27 \n",
- "28 na \n",
- "29 zwierzynieckÄ… \n",
- "30 na \n",
- "31 zwierzynieckÄ… \n",
- "32 ja \n",
- "33 z \n",
- "34 bródna \n",
- "35 z \n",
- "36 którego \n",
- "37 miejsca \n",
- "38 \n",
- "39 z \n",
- "40 bródna \n",
- "41 to \n",
- "42 jest \n",
- "43 ulica \n",
- "44 wyszogrodzka \n",
- "45 tu \n",
- "46 przy \n",
- "47 rembielińskiej \n",
- "48 czyli \n",
- "49 przy \n",
- "50 tramwajach \n",
- "51 \n",
- "52 \n",
- "53 przy \n",
- "54 tramwajach \n",
- "55 tak \n",
- "56 \n",
- "57 \n",
- "58 może \n",
- "59 sprawdzÄ™ \n",
- "60 dobrze \n",
- "61 dobrze \n",
- "62 \n",
- "63 \n",
- "64 podjedzie \n",
- "65 tramwajem \n",
- "66 do \n",
- "67 ronda \n",
- "68 żaba \n",
- "69 tak \n",
- "70 od \n",
- "71 ronda \n",
- "72 żaba \n",
- "73 już \n",
- "74 \n",
- "75 \n",
- "76 \n",
- "77 \n",
- "78 162 \n",
- "79 jest \n",
- "80 162 \n",
- "81 tak \n",
- "82 i \n",
- "83 \n",
- "84 \n",
- "85 162 \n",
- "86 tam \n",
- "87 dojadÄ™ \n",
- "88 do \n",
- "89 tej \n",
- "90 uli \n",
- "91 tak \n",
- "92 może \n",
- "93 pani \n",
- "94 wysiąść \n",
- "95 \n",
- "96 banku \n",
- "97 bartycka \n",
- "98 albo \n",
- "99 sielce \n",
- "100 bartycka \n",
- "101 albo \n",
- "102 \n",
- "103 sielce \n",
- "104 sielce \n",
- "105 tak \n",
- "106 \n",
- "107 tak \n",
- "108 aha \n",
- "109 i \n",
- "110 tam \n",
- "111 w \n",
- "112 pobliżu \n",
- "113 jest \n",
- "114 ta \n",
- "115 ulica \n",
- "116 \n",
- "117 zwierzyniecka \n",
- "118 ma \n",
- "119 pani \n",
- "120 zwierzyniecka \n",
- "121 telefonem \n",
- "122 \n",
- "123 dzikie \n",
- "124 który \n",
- "125 8 \n",
- "126 a \n",
- "127 zwierzyniecka \n",
- "128 \n",
- "129 \n",
- "130 to \n",
- "131 to \n",
- "132 \n",
- "133 przy \n",
- "134 sielce \n",
- "135 trza \n",
- "136 wysiąść \n",
- "137 przy \n",
- "138 sielce \n",
- "139 tak \n",
- "140 tak \n",
- "141 stanek \n",
- "142 sielce \n",
- "143 \n",
- "144 aha \n",
- "145 \n",
- "146 no \n",
- "147 dobrze \n",
- "148 a \n",
- "149 sielce \n",
- "150 \n",
- "151 \n",
- "152 jaka \n",
- "153 to \n",
- "154 już \n",
- "155 jest \n",
- "156 dzielnica \n",
- "157 to \n",
- "158 ta \n",
- "159 jest \n",
- "160 przy \n",
- "161 ulica \n",
- "162 gagarina \n",
- "163 a \n",
- "164 przy \n",
- "165 ulicy \n",
- "166 gagarina \n",
- "167 czyli \n",
- "168 to \n",
- "169 jest \n",
- "170 tam \n",
- "171 mokotów \n",
- "172 po \n",
- "173 prostu \n",
- "174 tak \n",
- "175 \n",
- "176 tak \n",
- "177 siekierki \n",
- "178 mokot \n",
- "179 siekierki \n",
- "180 mokot \n",
- "181 ów \n",
- "182 i \n",
- "183 tam \n",
- "184 jak \n",
- "185 pani \n",
- "186 wysiÄ…dzie \n",
- "187 to \n",
- "188 trza \n",
- "189 wejść \n",
- "190 \n",
- "191 \n",
- "192 \n",
- "193 scenerii \n",
- "194 \n",
- "195 i \n",
- "196 od \n",
- "197 nehru \n",
- "198 odchodzi \n",
- "199 zwierzyniecka \n",
- "200 w \n",
- "201 le \n",
- "202 w \n",
- "203 lewo \n",
- "204 i \n",
- "205 ulica \n",
- "206 \n",
- "207 nehru \n",
- "208 tak \n",
- "209 nehru \n",
- "210 dobrze \n",
- "211 dziękuję \n",
- "212 panu \n",
- "213 bardzo \n",
- "214 \n",
- "215 do \n",
- "216 widzenia \n",
- "217 to \n",
- "218 wszystko "
+ " step_type reference_word_text hypothesis_word_text\n",
+ "0 DELETION xxx \n",
+ "1 CORRECT dzień dzień\n",
+ "2 CORRECT dobry dobry\n",
+ "3 CORRECT dzień dzień\n",
+ "4 CORRECT dobry dobry\n",
+ "5 CORRECT proszÄ™ proszÄ™\n",
+ "6 CORRECT pana pana\n",
+ "7 CORRECT ja ja\n",
+ "8 CORRECT mam mam\n",
+ "9 INSERTION pytanie\n",
+ "10 CORRECT o o\n",
+ "11 CORRECT której której\n",
+ "12 CORRECT będzie będzie\n",
+ "13 DELETION sto \n",
+ "14 DELETION czterdzieści \n",
+ "15 SUBSTITUTION trzy 143\n",
+ "16 CORRECT będzie będzie\n",
+ "17 CORRECT najbliższy najbliższy\n",
+ "18 CORRECT z z\n",
+ "19 INSERTION alei\n",
+ "20 SUBSTITUTION Alei witosa\n",
+ "21 SUBSTITUTION Alei alei\n",
+ "22 SUBSTITUTION Witosa witosa\n",
+ "23 CORRECT w w\n",
+ "24 CORRECT stronÄ™ stronÄ™\n",
+ "25 DELETION Gocławia \n",
+ "26 DELETION z \n",
+ "27 SUBSTITUTION tego gocławia\n",
+ "28 CORRECT przystanku przystanku\n",
+ "29 DELETION vis \n",
+ "30 DELETION - \n",
+ "31 DELETION a \n",
+ "32 DELETION - \n",
+ "33 SUBSTITUTION vis widzowi\n",
+ "34 SUBSTITUTION ZUSu zusu\n",
+ "35 CORRECT tak tak\n",
+ "36 DELETION ? \n",
+ "37 CORRECT no no\n",
+ "38 CORRECT nie nie\n",
+ "39 CORRECT nie nie\n",
+ "40 CORRECT tam tam\n",
+ "41 DELETION vis \n",
+ "42 DELETION - \n",
+ "43 DELETION a \n",
+ "44 DELETION - \n",
+ "45 SUBSTITUTION vis widzowi\n",
+ "46 SUBSTITUTION Panoramy panoramy\n",
+ "47 CORRECT przez przez\n",
+ "48 SUBSTITUTION Siekierkowski siekierkowski\n",
+ "49 CORRECT tam tam\n",
+ "50 CORRECT w w\n",
+ "51 CORRECT stronÄ™ stronÄ™\n",
+ "52 SUBSTITUTION Gocławia gocławia\n",
+ "53 CORRECT ale ale\n",
+ "54 CORRECT to to\n",
+ "55 CORRECT nie nie\n",
+ "56 CORRECT z z\n",
+ "57 CORRECT tego tego\n",
+ "58 CORRECT przystanku przystanku\n",
+ "59 DELETION Aleja \n",
+ "60 SUBSTITUTION Witosa aleja\n",
+ "61 SUBSTITUTION ? witosa\n",
+ "62 CORRECT no no\n",
+ "63 CORRECT to to\n",
+ "64 CORRECT jest jest\n",
+ "65 CORRECT czy czy\n",
+ "66 SUBSTITUTION Bartoszka bartoszka\n",
+ "67 CORRECT na na\n",
+ "68 CORRECT żądanie żądanie\n",
+ "69 CORRECT wie wie\n",
+ "70 CORRECT pan pan\n",
+ "71 CORRECT gdzie gdzie\n",
+ "72 CORRECT jest jest\n",
+ "73 CORRECT siÄ™ siÄ™\n",
+ "74 CORRECT zaczyna zaczyna\n",
+ "75 SUBSTITUTION Most most\n",
+ "76 SUBSTITUTION Siekierkowski siekierkowski\n",
+ "77 CORRECT tam tam\n",
+ "78 CORRECT w w\n",
+ "79 CORRECT stronÄ™ stronÄ™\n",
+ "80 DELETION Gocławia \n",
+ "81 DELETION gdzie \n",
+ "82 SUBSTITUTION ma wrocław\n",
+ "83 CORRECT on on\n",
+ "84 CORRECT przystanek przystanek\n",
+ "85 CORRECT pierwszy pierwszy\n",
+ "86 DELETION sto \n",
+ "87 DELETION czterdzieści \n",
+ "88 SUBSTITUTION trzy 143\n",
+ "89 CORRECT znaczy znaczy\n",
+ "90 CORRECT tak tak\n",
+ "91 CORRECT naprawdÄ™ naprawdÄ™\n",
+ "92 SUBSTITUTION Most most\n",
+ "93 SUBSTITUTION Siekierkowski siekierkowski\n",
+ "94 CORRECT to to\n",
+ "95 CORRECT siÄ™ siÄ™\n",
+ "96 CORRECT zaczyna zaczyna\n",
+ "97 CORRECT za za\n",
+ "98 SUBSTITUTION Siekierki siekierki\n",
+ "99 SUBSTITUTION Sanktuarium sanktuarium\n",
+ "100 CORRECT no no\n",
+ "101 CORRECT właśnie właśnie\n",
+ "102 CORRECT przed przed\n",
+ "103 CORRECT tym tym\n",
+ "104 CORRECT przed przed\n",
+ "105 CORRECT tym tym\n",
+ "106 CORRECT przystanek przystanek\n",
+ "107 CORRECT o o\n",
+ "108 CORRECT której której\n",
+ "109 CORRECT jest jest\n",
+ "110 DELETION sto \n",
+ "111 DELETION czterdzieści \n",
+ "112 SUBSTITUTION trzy 143\n",
+ "113 CORRECT najbliższy najbliższy\n",
+ "114 DELETION aha \n",
+ "115 DELETION czyli \n",
+ "116 DELETION to \n",
+ "117 CORRECT wtedy wtedy\n",
+ "118 CORRECT przystanek przystanek\n",
+ "119 SUBSTITUTION Małe małe\n",
+ "120 SUBSTITUTION Siekierki siekierki\n",
+ "121 CORRECT ale ale\n",
+ "122 CORRECT to to\n",
+ "123 CORRECT nie nie\n",
+ "124 CORRECT jest jest\n",
+ "125 DELETION tak \n",
+ "126 DELETION tak \n",
+ "127 DELETION tak \n",
+ "128 DELETION tak \n",
+ "129 DELETION na \n",
+ "130 DELETION wysokości \n",
+ "131 SUBSTITUTION Panoramy dokonać\n",
+ "132 SUBSTITUTION aha panoramy\n",
+ "133 CORRECT dobrze dobrze\n",
+ "134 CORRECT najbliższy najbliższy\n",
+ "135 CORRECT już już\n",
+ "136 CORRECT chwileczkÄ™ chwileczkÄ™\n",
+ "137 CORRECT czternasta czternasta\n",
+ "138 DELETION czterdzieści \n",
+ "139 SUBSTITUTION sześć 46\n",
+ "140 CORRECT piętnasta piętnasta\n",
+ "141 SUBSTITUTION zero 0\n",
+ "142 SUBSTITUTION jeden 1\n",
+ "143 CORRECT aha aha\n",
+ "144 DELETION no \n",
+ "145 CORRECT dobrze dobrze\n",
+ "146 CORRECT dziękuję dziękuję\n",
+ "147 DELETION do \n",
+ "148 DELETION widzenia \n",
+ "149 CORRECT do do\n",
+ "150 CORRECT widzenia widzenia"
]
},
"metadata": {},
@@ -4223,2934 +4136,3398 @@
" <tr>\n",
" <th>0</th>\n",
" <td>DELETION</td>\n",
- " <td>xxx</td>\n",
+ " <td>_</td>\n",
" <td></td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
- " <td>CORRECT</td>\n",
- " <td>dzień</td>\n",
- " <td>dzień</td>\n",
+ " <td>DELETION</td>\n",
+ " <td>_</td>\n",
+ " <td></td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
- " <td>CORRECT</td>\n",
- " <td>dobry</td>\n",
- " <td>dobry</td>\n",
+ " <td>DELETION</td>\n",
+ " <td>_</td>\n",
+ " <td></td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
- " <td>CORRECT</td>\n",
- " <td>dzień</td>\n",
- " <td>dzień</td>\n",
+ " <td>DELETION</td>\n",
+ " <td>_</td>\n",
+ " <td></td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
- " <td>CORRECT</td>\n",
- " <td>dobry</td>\n",
- " <td>dobry</td>\n",
+ " <td>DELETION</td>\n",
+ " <td>_</td>\n",
+ " <td></td>\n",
" </tr>\n",
" <tr>\n",
" <th>5</th>\n",
" <td>CORRECT</td>\n",
- " <td>proszÄ™</td>\n",
- " <td>proszÄ™</td>\n",
+ " <td>_</td>\n",
+ " <td>_</td>\n",
" </tr>\n",
" <tr>\n",
" <th>6</th>\n",
" <td>CORRECT</td>\n",
- " <td>pana</td>\n",
- " <td>pana</td>\n",
+ " <td>_</td>\n",
+ " <td>_</td>\n",
" </tr>\n",
" <tr>\n",
" <th>7</th>\n",
" <td>CORRECT</td>\n",
- " <td>ja</td>\n",
- " <td>ja</td>\n",
+ " <td>_</td>\n",
+ " <td>_</td>\n",
" </tr>\n",
" <tr>\n",
" <th>8</th>\n",
" <td>CORRECT</td>\n",
- " <td>chciałam</td>\n",
- " <td>chciałam</td>\n",
+ " <td>_</td>\n",
+ " <td>_</td>\n",
" </tr>\n",
" <tr>\n",
" <th>9</th>\n",
" <td>CORRECT</td>\n",
- " <td>siÄ™</td>\n",
- " <td>siÄ™</td>\n",
+ " <td>_</td>\n",
+ " <td>_</td>\n",
" </tr>\n",
" <tr>\n",
" <th>10</th>\n",
" <td>CORRECT</td>\n",
- " <td>dowiedzieć</td>\n",
- " <td>dowiedzieć</td>\n",
+ " <td>_</td>\n",
+ " <td>_</td>\n",
" </tr>\n",
" <tr>\n",
" <th>11</th>\n",
" <td>CORRECT</td>\n",
- " <td>bo</td>\n",
- " <td>bo</td>\n",
+ " <td>_</td>\n",
+ " <td>_</td>\n",
" </tr>\n",
" <tr>\n",
" <th>12</th>\n",
" <td>CORRECT</td>\n",
- " <td>nie</td>\n",
- " <td>nie</td>\n",
+ " <td>_</td>\n",
+ " <td>_</td>\n",
" </tr>\n",
" <tr>\n",
" <th>13</th>\n",
" <td>CORRECT</td>\n",
- " <td>bardzo</td>\n",
- " <td>bardzo</td>\n",
+ " <td>_</td>\n",
+ " <td>_</td>\n",
" </tr>\n",
" <tr>\n",
" <th>14</th>\n",
" <td>CORRECT</td>\n",
- " <td>wiem</td>\n",
- " <td>wiem</td>\n",
+ " <td>_</td>\n",
+ " <td>_</td>\n",
" </tr>\n",
" <tr>\n",
" <th>15</th>\n",
" <td>CORRECT</td>\n",
- " <td>gdzie</td>\n",
- " <td>gdzie</td>\n",
+ " <td>_</td>\n",
+ " <td>_</td>\n",
" </tr>\n",
" <tr>\n",
" <th>16</th>\n",
" <td>CORRECT</td>\n",
- " <td>znajduje</td>\n",
- " <td>znajduje</td>\n",
+ " <td>_</td>\n",
+ " <td>_</td>\n",
" </tr>\n",
" <tr>\n",
" <th>17</th>\n",
" <td>CORRECT</td>\n",
- " <td>siÄ™</td>\n",
- " <td>siÄ™</td>\n",
+ " <td>_</td>\n",
+ " <td>_</td>\n",
" </tr>\n",
" <tr>\n",
" <th>18</th>\n",
- " <td>CORRECT</td>\n",
- " <td>ulica</td>\n",
- " <td>ulica</td>\n",
+ " <td>DELETION</td>\n",
+ " <td>geogName</td>\n",
+ " <td></td>\n",
" </tr>\n",
" <tr>\n",
" <th>19</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>Zwierzyniecka</td>\n",
- " <td>zwierzyniecka</td>\n",
+ " <td>DELETION</td>\n",
+ " <td>geogName</td>\n",
+ " <td></td>\n",
" </tr>\n",
" <tr>\n",
" <th>20</th>\n",
- " <td>CORRECT</td>\n",
- " <td>i</td>\n",
- " <td>i</td>\n",
+ " <td>DELETION</td>\n",
+ " <td>geogName</td>\n",
+ " <td></td>\n",
" </tr>\n",
" <tr>\n",
" <th>21</th>\n",
" <td>CORRECT</td>\n",
- " <td>jak</td>\n",
- " <td>jak</td>\n",
+ " <td>_</td>\n",
+ " <td>_</td>\n",
" </tr>\n",
" <tr>\n",
" <th>22</th>\n",
" <td>CORRECT</td>\n",
- " <td>dojechać</td>\n",
- " <td>dojechać</td>\n",
+ " <td>_</td>\n",
+ " <td>_</td>\n",
" </tr>\n",
" <tr>\n",
" <th>23</th>\n",
- " <td>CORRECT</td>\n",
- " <td>z</td>\n",
- " <td>z</td>\n",
+ " <td>DELETION</td>\n",
+ " <td>placeName</td>\n",
+ " <td></td>\n",
" </tr>\n",
" <tr>\n",
" <th>24</th>\n",
- " <td>DELETION</td>\n",
- " <td>Bródna</td>\n",
- " <td></td>\n",
+ " <td>CORRECT</td>\n",
+ " <td>_</td>\n",
+ " <td>_</td>\n",
" </tr>\n",
" <tr>\n",
" <th>25</th>\n",
- " <td>DELETION</td>\n",
- " <td>na</td>\n",
- " <td></td>\n",
+ " <td>CORRECT</td>\n",
+ " <td>_</td>\n",
+ " <td>_</td>\n",
" </tr>\n",
" <tr>\n",
" <th>26</th>\n",
- " <td>DELETION</td>\n",
- " <td>przykład</td>\n",
- " <td></td>\n",
+ " <td>CORRECT</td>\n",
+ " <td>_</td>\n",
+ " <td>_</td>\n",
" </tr>\n",
" <tr>\n",
" <th>27</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>?</td>\n",
- " <td>bródna</td>\n",
+ " <td>CORRECT</td>\n",
+ " <td>_</td>\n",
+ " <td>_</td>\n",
" </tr>\n",
" <tr>\n",
" <th>28</th>\n",
" <td>CORRECT</td>\n",
- " <td>na</td>\n",
- " <td>na</td>\n",
+ " <td>_</td>\n",
+ " <td>_</td>\n",
" </tr>\n",
" <tr>\n",
" <th>29</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>ZwierzynieckÄ…</td>\n",
- " <td>zwierzynieckÄ…</td>\n",
+ " <td>CORRECT</td>\n",
+ " <td>_</td>\n",
+ " <td>_</td>\n",
" </tr>\n",
" <tr>\n",
" <th>30</th>\n",
" <td>CORRECT</td>\n",
- " <td>na</td>\n",
- " <td>na</td>\n",
+ " <td>_</td>\n",
+ " <td>_</td>\n",
" </tr>\n",
" <tr>\n",
" <th>31</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>ZwierzynieckÄ…</td>\n",
- " <td>zwierzynieckÄ…</td>\n",
+ " <td>CORRECT</td>\n",
+ " <td>_</td>\n",
+ " <td>_</td>\n",
" </tr>\n",
" <tr>\n",
" <th>32</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>a</td>\n",
- " <td>ja</td>\n",
+ " <td>DELETION</td>\n",
+ " <td>orgName</td>\n",
+ " <td></td>\n",
" </tr>\n",
" <tr>\n",
" <th>33</th>\n",
" <td>CORRECT</td>\n",
- " <td>z</td>\n",
- " <td>z</td>\n",
+ " <td>_</td>\n",
+ " <td>_</td>\n",
" </tr>\n",
" <tr>\n",
" <th>34</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>Bródna</td>\n",
- " <td>bródna</td>\n",
+ " <td>CORRECT</td>\n",
+ " <td>_</td>\n",
+ " <td>_</td>\n",
" </tr>\n",
" <tr>\n",
" <th>35</th>\n",
" <td>CORRECT</td>\n",
- " <td>z</td>\n",
- " <td>z</td>\n",
+ " <td>_</td>\n",
+ " <td>_</td>\n",
" </tr>\n",
" <tr>\n",
" <th>36</th>\n",
" <td>CORRECT</td>\n",
- " <td>którego</td>\n",
- " <td>którego</td>\n",
+ " <td>_</td>\n",
+ " <td>_</td>\n",
" </tr>\n",
" <tr>\n",
" <th>37</th>\n",
" <td>CORRECT</td>\n",
- " <td>miejsca</td>\n",
- " <td>miejsca</td>\n",
+ " <td>_</td>\n",
+ " <td>_</td>\n",
" </tr>\n",
" <tr>\n",
" <th>38</th>\n",
- " <td>DELETION</td>\n",
- " <td>?</td>\n",
- " <td></td>\n",
+ " <td>CORRECT</td>\n",
+ " <td>_</td>\n",
+ " <td>_</td>\n",
" </tr>\n",
" <tr>\n",
" <th>39</th>\n",
" <td>CORRECT</td>\n",
- " <td>z</td>\n",
- " <td>z</td>\n",
+ " <td>_</td>\n",
+ " <td>_</td>\n",
" </tr>\n",
" <tr>\n",
" <th>40</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>Bródna</td>\n",
- " <td>bródna</td>\n",
+ " <td>CORRECT</td>\n",
+ " <td>_</td>\n",
+ " <td>_</td>\n",
" </tr>\n",
" <tr>\n",
" <th>41</th>\n",
" <td>CORRECT</td>\n",
- " <td>to</td>\n",
- " <td>to</td>\n",
+ " <td>_</td>\n",
+ " <td>_</td>\n",
" </tr>\n",
" <tr>\n",
" <th>42</th>\n",
" <td>CORRECT</td>\n",
- " <td>jest</td>\n",
- " <td>jest</td>\n",
+ " <td>_</td>\n",
+ " <td>_</td>\n",
" </tr>\n",
" <tr>\n",
" <th>43</th>\n",
- " <td>CORRECT</td>\n",
- " <td>ulica</td>\n",
- " <td>ulica</td>\n",
+ " <td>DELETION</td>\n",
+ " <td>geogName</td>\n",
+ " <td></td>\n",
" </tr>\n",
" <tr>\n",
" <th>44</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>Wyszogrodzka</td>\n",
- " <td>wyszogrodzka</td>\n",
+ " <td>DELETION</td>\n",
+ " <td>geogName</td>\n",
+ " <td></td>\n",
" </tr>\n",
" <tr>\n",
" <th>45</th>\n",
" <td>CORRECT</td>\n",
- " <td>tu</td>\n",
- " <td>tu</td>\n",
+ " <td>_</td>\n",
+ " <td>_</td>\n",
" </tr>\n",
" <tr>\n",
" <th>46</th>\n",
" <td>CORRECT</td>\n",
- " <td>przy</td>\n",
- " <td>przy</td>\n",
+ " <td>placeName</td>\n",
+ " <td>placeName</td>\n",
" </tr>\n",
" <tr>\n",
" <th>47</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>Rembielińskiej</td>\n",
- " <td>rembielińskiej</td>\n",
+ " <td>CORRECT</td>\n",
+ " <td>_</td>\n",
+ " <td>_</td>\n",
" </tr>\n",
" <tr>\n",
" <th>48</th>\n",
" <td>CORRECT</td>\n",
- " <td>czyli</td>\n",
- " <td>czyli</td>\n",
+ " <td>_</td>\n",
+ " <td>_</td>\n",
" </tr>\n",
" <tr>\n",
" <th>49</th>\n",
" <td>CORRECT</td>\n",
- " <td>przy</td>\n",
- " <td>przy</td>\n",
+ " <td>_</td>\n",
+ " <td>_</td>\n",
" </tr>\n",
" <tr>\n",
" <th>50</th>\n",
- " <td>CORRECT</td>\n",
- " <td>tramwajach</td>\n",
- " <td>tramwajach</td>\n",
+ " <td>DELETION</td>\n",
+ " <td>placeName</td>\n",
+ " <td></td>\n",
" </tr>\n",
" <tr>\n",
" <th>51</th>\n",
- " <td>DELETION</td>\n",
- " <td>tak</td>\n",
- " <td></td>\n",
+ " <td>CORRECT</td>\n",
+ " <td>_</td>\n",
+ " <td>_</td>\n",
" </tr>\n",
" <tr>\n",
" <th>52</th>\n",
- " <td>DELETION</td>\n",
- " <td>?</td>\n",
- " <td></td>\n",
+ " <td>CORRECT</td>\n",
+ " <td>_</td>\n",
+ " <td>_</td>\n",
" </tr>\n",
" <tr>\n",
" <th>53</th>\n",
" <td>CORRECT</td>\n",
- " <td>przy</td>\n",
- " <td>przy</td>\n",
+ " <td>_</td>\n",
+ " <td>_</td>\n",
" </tr>\n",
" <tr>\n",
" <th>54</th>\n",
" <td>CORRECT</td>\n",
- " <td>tramwajach</td>\n",
- " <td>tramwajach</td>\n",
+ " <td>_</td>\n",
+ " <td>_</td>\n",
" </tr>\n",
" <tr>\n",
" <th>55</th>\n",
" <td>CORRECT</td>\n",
- " <td>tak</td>\n",
- " <td>tak</td>\n",
+ " <td>_</td>\n",
+ " <td>_</td>\n",
" </tr>\n",
" <tr>\n",
" <th>56</th>\n",
" <td>CORRECT</td>\n",
- " <td>może</td>\n",
- " <td>może</td>\n",
+ " <td>_</td>\n",
+ " <td>_</td>\n",
" </tr>\n",
" <tr>\n",
" <th>57</th>\n",
" <td>DELETION</td>\n",
- " <td>pani</td>\n",
+ " <td>geogName</td>\n",
" <td></td>\n",
" </tr>\n",
" <tr>\n",
" <th>58</th>\n",
- " <td>DELETION</td>\n",
- " <td>poczeka</td>\n",
- " <td></td>\n",
+ " <td>CORRECT</td>\n",
+ " <td>_</td>\n",
+ " <td>_</td>\n",
" </tr>\n",
" <tr>\n",
" <th>59</th>\n",
" <td>CORRECT</td>\n",
- " <td>sprawdzÄ™</td>\n",
- " <td>sprawdzÄ™</td>\n",
+ " <td>_</td>\n",
+ " <td>_</td>\n",
" </tr>\n",
" <tr>\n",
" <th>60</th>\n",
" <td>CORRECT</td>\n",
- " <td>dobrze</td>\n",
- " <td>dobrze</td>\n",
+ " <td>_</td>\n",
+ " <td>_</td>\n",
" </tr>\n",
" <tr>\n",
" <th>61</th>\n",
" <td>CORRECT</td>\n",
- " <td>dobrze</td>\n",
- " <td>dobrze</td>\n",
+ " <td>_</td>\n",
+ " <td>_</td>\n",
" </tr>\n",
" <tr>\n",
" <th>62</th>\n",
- " <td>DELETION</td>\n",
- " <td>pani</td>\n",
- " <td></td>\n",
+ " <td>CORRECT</td>\n",
+ " <td>_</td>\n",
+ " <td>_</td>\n",
" </tr>\n",
" <tr>\n",
" <th>63</th>\n",
- " <td>DELETION</td>\n",
- " <td>sobie</td>\n",
- " <td></td>\n",
+ " <td>CORRECT</td>\n",
+ " <td>_</td>\n",
+ " <td>_</td>\n",
" </tr>\n",
" <tr>\n",
" <th>64</th>\n",
- " <td>CORRECT</td>\n",
- " <td>podjedzie</td>\n",
- " <td>podjedzie</td>\n",
+ " <td>DELETION</td>\n",
+ " <td>persName</td>\n",
+ " <td></td>\n",
" </tr>\n",
" <tr>\n",
" <th>65</th>\n",
" <td>CORRECT</td>\n",
- " <td>tramwajem</td>\n",
- " <td>tramwajem</td>\n",
+ " <td>_</td>\n",
+ " <td>_</td>\n",
" </tr>\n",
" <tr>\n",
" <th>66</th>\n",
" <td>CORRECT</td>\n",
- " <td>do</td>\n",
- " <td>do</td>\n",
+ " <td>_</td>\n",
+ " <td>_</td>\n",
" </tr>\n",
" <tr>\n",
" <th>67</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>Ronda</td>\n",
- " <td>ronda</td>\n",
+ " <td>CORRECT</td>\n",
+ " <td>_</td>\n",
+ " <td>_</td>\n",
" </tr>\n",
" <tr>\n",
" <th>68</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>Żaba</td>\n",
- " <td>żaba</td>\n",
+ " <td>CORRECT</td>\n",
+ " <td>_</td>\n",
+ " <td>_</td>\n",
" </tr>\n",
" <tr>\n",
" <th>69</th>\n",
" <td>CORRECT</td>\n",
- " <td>tak</td>\n",
- " <td>tak</td>\n",
+ " <td>_</td>\n",
+ " <td>_</td>\n",
" </tr>\n",
" <tr>\n",
" <th>70</th>\n",
" <td>CORRECT</td>\n",
- " <td>od</td>\n",
- " <td>od</td>\n",
+ " <td>_</td>\n",
+ " <td>_</td>\n",
" </tr>\n",
" <tr>\n",
" <th>71</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>Ronda</td>\n",
- " <td>ronda</td>\n",
+ " <td>CORRECT</td>\n",
+ " <td>_</td>\n",
+ " <td>_</td>\n",
" </tr>\n",
" <tr>\n",
" <th>72</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>Żaba</td>\n",
- " <td>żaba</td>\n",
+ " <td>CORRECT</td>\n",
+ " <td>_</td>\n",
+ " <td>_</td>\n",
" </tr>\n",
" <tr>\n",
" <th>73</th>\n",
- " <td>CORRECT</td>\n",
- " <td>już</td>\n",
- " <td>już</td>\n",
+ " <td>DELETION</td>\n",
+ " <td>geogName</td>\n",
+ " <td></td>\n",
" </tr>\n",
" <tr>\n",
" <th>74</th>\n",
" <td>DELETION</td>\n",
- " <td>sto</td>\n",
+ " <td>geogName</td>\n",
" <td></td>\n",
" </tr>\n",
" <tr>\n",
" <th>75</th>\n",
- " <td>DELETION</td>\n",
- " <td>sześćdziesiąt</td>\n",
- " <td></td>\n",
+ " <td>CORRECT</td>\n",
+ " <td>_</td>\n",
+ " <td>_</td>\n",
" </tr>\n",
" <tr>\n",
" <th>76</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>dwa</td>\n",
- " <td>162</td>\n",
+ " <td>CORRECT</td>\n",
+ " <td>_</td>\n",
+ " <td>_</td>\n",
" </tr>\n",
" <tr>\n",
" <th>77</th>\n",
" <td>CORRECT</td>\n",
- " <td>jest</td>\n",
- " <td>jest</td>\n",
+ " <td>_</td>\n",
+ " <td>_</td>\n",
" </tr>\n",
" <tr>\n",
" <th>78</th>\n",
- " <td>DELETION</td>\n",
- " <td>sto</td>\n",
- " <td></td>\n",
+ " <td>CORRECT</td>\n",
+ " <td>placeName</td>\n",
+ " <td>placeName</td>\n",
" </tr>\n",
" <tr>\n",
" <th>79</th>\n",
" <td>DELETION</td>\n",
- " <td>sześćdziesiąt</td>\n",
+ " <td>_</td>\n",
" <td></td>\n",
" </tr>\n",
" <tr>\n",
" <th>80</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>dwa</td>\n",
- " <td>162</td>\n",
+ " <td>DELETION</td>\n",
+ " <td>_</td>\n",
+ " <td></td>\n",
" </tr>\n",
" <tr>\n",
" <th>81</th>\n",
- " <td>CORRECT</td>\n",
- " <td>tak</td>\n",
- " <td>tak</td>\n",
+ " <td>DELETION</td>\n",
+ " <td>_</td>\n",
+ " <td></td>\n",
" </tr>\n",
" <tr>\n",
" <th>82</th>\n",
- " <td>CORRECT</td>\n",
- " <td>i</td>\n",
- " <td>i</td>\n",
+ " <td>DELETION</td>\n",
+ " <td>_</td>\n",
+ " <td></td>\n",
" </tr>\n",
" <tr>\n",
" <th>83</th>\n",
- " <td>DELETION</td>\n",
- " <td>sto</td>\n",
- " <td></td>\n",
+ " <td>CORRECT</td>\n",
+ " <td>_</td>\n",
+ " <td>_</td>\n",
" </tr>\n",
" <tr>\n",
" <th>84</th>\n",
- " <td>DELETION</td>\n",
- " <td>sześćdziesiąt</td>\n",
- " <td></td>\n",
+ " <td>CORRECT</td>\n",
+ " <td>_</td>\n",
+ " <td>_</td>\n",
" </tr>\n",
" <tr>\n",
" <th>85</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>dwa</td>\n",
- " <td>162</td>\n",
+ " <td>CORRECT</td>\n",
+ " <td>_</td>\n",
+ " <td>_</td>\n",
" </tr>\n",
" <tr>\n",
" <th>86</th>\n",
- " <td>CORRECT</td>\n",
- " <td>tam</td>\n",
- " <td>tam</td>\n",
+ " <td>SUBSTITUTION</td>\n",
+ " <td>_</td>\n",
+ " <td>placeName</td>\n",
" </tr>\n",
" <tr>\n",
" <th>87</th>\n",
" <td>CORRECT</td>\n",
- " <td>dojadÄ™</td>\n",
- " <td>dojadÄ™</td>\n",
+ " <td>_</td>\n",
+ " <td>_</td>\n",
" </tr>\n",
" <tr>\n",
" <th>88</th>\n",
" <td>CORRECT</td>\n",
- " <td>do</td>\n",
- " <td>do</td>\n",
+ " <td>_</td>\n",
+ " <td>_</td>\n",
" </tr>\n",
" <tr>\n",
" <th>89</th>\n",
" <td>CORRECT</td>\n",
- " <td>tej</td>\n",
- " <td>tej</td>\n",
+ " <td>_</td>\n",
+ " <td>_</td>\n",
" </tr>\n",
" <tr>\n",
" <th>90</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>ulicy</td>\n",
- " <td>uli</td>\n",
+ " <td>DELETION</td>\n",
+ " <td>geogName</td>\n",
+ " <td></td>\n",
" </tr>\n",
" <tr>\n",
" <th>91</th>\n",
- " <td>CORRECT</td>\n",
- " <td>tak</td>\n",
- " <td>tak</td>\n",
+ " <td>DELETION</td>\n",
+ " <td>geogName</td>\n",
+ " <td></td>\n",
" </tr>\n",
" <tr>\n",
" <th>92</th>\n",
" <td>CORRECT</td>\n",
- " <td>może</td>\n",
- " <td>może</td>\n",
+ " <td>_</td>\n",
+ " <td>_</td>\n",
" </tr>\n",
" <tr>\n",
" <th>93</th>\n",
" <td>CORRECT</td>\n",
- " <td>pani</td>\n",
- " <td>pani</td>\n",
+ " <td>_</td>\n",
+ " <td>_</td>\n",
" </tr>\n",
" <tr>\n",
" <th>94</th>\n",
" <td>CORRECT</td>\n",
- " <td>wysiąść</td>\n",
- " <td>wysiąść</td>\n",
+ " <td>_</td>\n",
+ " <td>_</td>\n",
" </tr>\n",
" <tr>\n",
" <th>95</th>\n",
- " <td>DELETION</td>\n",
- " <td>na</td>\n",
- " <td></td>\n",
+ " <td>CORRECT</td>\n",
+ " <td>_</td>\n",
+ " <td>_</td>\n",
" </tr>\n",
" <tr>\n",
" <th>96</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>przystanku</td>\n",
- " <td>banku</td>\n",
+ " <td>DELETION</td>\n",
+ " <td>orgName</td>\n",
+ " <td></td>\n",
" </tr>\n",
" <tr>\n",
" <th>97</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>Bartycka</td>\n",
- " <td>bartycka</td>\n",
+ " <td>DELETION</td>\n",
+ " <td>orgName</td>\n",
+ " <td></td>\n",
" </tr>\n",
" <tr>\n",
" <th>98</th>\n",
" <td>CORRECT</td>\n",
- " <td>albo</td>\n",
- " <td>albo</td>\n",
+ " <td>_</td>\n",
+ " <td>_</td>\n",
" </tr>\n",
" <tr>\n",
" <th>99</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>Sielce</td>\n",
- " <td>sielce</td>\n",
+ " <td>CORRECT</td>\n",
+ " <td>_</td>\n",
+ " <td>_</td>\n",
" </tr>\n",
" <tr>\n",
" <th>100</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>Bartycka</td>\n",
- " <td>bartycka</td>\n",
+ " <td>CORRECT</td>\n",
+ " <td>_</td>\n",
+ " <td>_</td>\n",
" </tr>\n",
" <tr>\n",
" <th>101</th>\n",
" <td>CORRECT</td>\n",
- " <td>albo</td>\n",
- " <td>albo</td>\n",
+ " <td>_</td>\n",
+ " <td>_</td>\n",
" </tr>\n",
" <tr>\n",
" <th>102</th>\n",
- " <td>DELETION</td>\n",
- " <td>?</td>\n",
- " <td></td>\n",
+ " <td>CORRECT</td>\n",
+ " <td>_</td>\n",
+ " <td>_</td>\n",
" </tr>\n",
" <tr>\n",
" <th>103</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>Sielce</td>\n",
- " <td>sielce</td>\n",
+ " <td>CORRECT</td>\n",
+ " <td>_</td>\n",
+ " <td>_</td>\n",
" </tr>\n",
" <tr>\n",
" <th>104</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>Sielce</td>\n",
- " <td>sielce</td>\n",
+ " <td>CORRECT</td>\n",
+ " <td>_</td>\n",
+ " <td>_</td>\n",
" </tr>\n",
" <tr>\n",
" <th>105</th>\n",
" <td>CORRECT</td>\n",
- " <td>tak</td>\n",
- " <td>tak</td>\n",
+ " <td>_</td>\n",
+ " <td>_</td>\n",
" </tr>\n",
" <tr>\n",
" <th>106</th>\n",
- " <td>DELETION</td>\n",
- " <td>?</td>\n",
- " <td></td>\n",
+ " <td>CORRECT</td>\n",
+ " <td>_</td>\n",
+ " <td>_</td>\n",
" </tr>\n",
" <tr>\n",
" <th>107</th>\n",
" <td>CORRECT</td>\n",
- " <td>tak</td>\n",
- " <td>tak</td>\n",
+ " <td>_</td>\n",
+ " <td>_</td>\n",
" </tr>\n",
" <tr>\n",
" <th>108</th>\n",
" <td>CORRECT</td>\n",
- " <td>aha</td>\n",
- " <td>aha</td>\n",
+ " <td>_</td>\n",
+ " <td>_</td>\n",
" </tr>\n",
" <tr>\n",
" <th>109</th>\n",
" <td>CORRECT</td>\n",
- " <td>i</td>\n",
- " <td>i</td>\n",
+ " <td>_</td>\n",
+ " <td>_</td>\n",
" </tr>\n",
" <tr>\n",
" <th>110</th>\n",
" <td>CORRECT</td>\n",
- " <td>tam</td>\n",
- " <td>tam</td>\n",
+ " <td>_</td>\n",
+ " <td>_</td>\n",
" </tr>\n",
" <tr>\n",
" <th>111</th>\n",
" <td>CORRECT</td>\n",
- " <td>w</td>\n",
- " <td>w</td>\n",
+ " <td>_</td>\n",
+ " <td>_</td>\n",
" </tr>\n",
" <tr>\n",
" <th>112</th>\n",
" <td>CORRECT</td>\n",
- " <td>pobliżu</td>\n",
- " <td>pobliżu</td>\n",
+ " <td>_</td>\n",
+ " <td>_</td>\n",
" </tr>\n",
" <tr>\n",
" <th>113</th>\n",
" <td>CORRECT</td>\n",
- " <td>jest</td>\n",
- " <td>jest</td>\n",
+ " <td>_</td>\n",
+ " <td>_</td>\n",
" </tr>\n",
" <tr>\n",
" <th>114</th>\n",
" <td>CORRECT</td>\n",
- " <td>ta</td>\n",
- " <td>ta</td>\n",
+ " <td>_</td>\n",
+ " <td>_</td>\n",
" </tr>\n",
" <tr>\n",
" <th>115</th>\n",
" <td>CORRECT</td>\n",
- " <td>ulica</td>\n",
- " <td>ulica</td>\n",
+ " <td>_</td>\n",
+ " <td>_</td>\n",
" </tr>\n",
" <tr>\n",
" <th>116</th>\n",
- " <td>DELETION</td>\n",
- " <td>tak</td>\n",
- " <td></td>\n",
+ " <td>CORRECT</td>\n",
+ " <td>_</td>\n",
+ " <td>_</td>\n",
" </tr>\n",
" <tr>\n",
" <th>117</th>\n",
" <td>DELETION</td>\n",
- " <td>?</td>\n",
+ " <td>placeName</td>\n",
" <td></td>\n",
" </tr>\n",
" <tr>\n",
" <th>118</th>\n",
" <td>DELETION</td>\n",
- " <td>a</td>\n",
+ " <td>placeName</td>\n",
" <td></td>\n",
" </tr>\n",
" <tr>\n",
" <th>119</th>\n",
- " <td>DELETION</td>\n",
- " <td>Zwierzyniecka</td>\n",
- " <td></td>\n",
+ " <td>CORRECT</td>\n",
+ " <td>_</td>\n",
+ " <td>_</td>\n",
" </tr>\n",
" <tr>\n",
" <th>120</th>\n",
- " <td>DELETION</td>\n",
- " <td>wysoki</td>\n",
- " <td></td>\n",
+ " <td>CORRECT</td>\n",
+ " <td>_</td>\n",
+ " <td>_</td>\n",
" </tr>\n",
" <tr>\n",
" <th>121</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>numer</td>\n",
- " <td>zwierzyniecka</td>\n",
+ " <td>CORRECT</td>\n",
+ " <td>_</td>\n",
+ " <td>_</td>\n",
" </tr>\n",
" <tr>\n",
" <th>122</th>\n",
" <td>CORRECT</td>\n",
- " <td>ma</td>\n",
- " <td>ma</td>\n",
+ " <td>_</td>\n",
+ " <td>_</td>\n",
" </tr>\n",
" <tr>\n",
" <th>123</th>\n",
" <td>CORRECT</td>\n",
- " <td>pani</td>\n",
- " <td>pani</td>\n",
+ " <td>_</td>\n",
+ " <td>_</td>\n",
" </tr>\n",
" <tr>\n",
" <th>124</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>?</td>\n",
- " <td>zwierzyniecka</td>\n",
+ " <td>CORRECT</td>\n",
+ " <td>_</td>\n",
+ " <td>_</td>\n",
" </tr>\n",
" <tr>\n",
" <th>125</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>Zwierzyniecka</td>\n",
- " <td>telefonem</td>\n",
+ " <td>CORRECT</td>\n",
+ " <td>_</td>\n",
+ " <td>_</td>\n",
" </tr>\n",
" <tr>\n",
" <th>126</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>zaraz</td>\n",
- " <td>dzikie</td>\n",
+ " <td>CORRECT</td>\n",
+ " <td>_</td>\n",
+ " <td>_</td>\n",
" </tr>\n",
" <tr>\n",
" <th>127</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>momencik</td>\n",
- " <td>który</td>\n",
+ " <td>CORRECT</td>\n",
+ " <td>_</td>\n",
+ " <td>_</td>\n",
" </tr>\n",
" <tr>\n",
" <th>128</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>osiem</td>\n",
- " <td>8</td>\n",
+ " <td>CORRECT</td>\n",
+ " <td>_</td>\n",
+ " <td>_</td>\n",
" </tr>\n",
" <tr>\n",
" <th>129</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>A</td>\n",
- " <td>a</td>\n",
+ " <td>DELETION</td>\n",
+ " <td>geogName</td>\n",
+ " <td></td>\n",
" </tr>\n",
" <tr>\n",
" <th>130</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>Zwierzyniecka</td>\n",
- " <td>zwierzyniecka</td>\n",
+ " <td>CORRECT</td>\n",
+ " <td>_</td>\n",
+ " <td>_</td>\n",
" </tr>\n",
" <tr>\n",
" <th>131</th>\n",
" <td>CORRECT</td>\n",
- " <td>to</td>\n",
- " <td>to</td>\n",
+ " <td>_</td>\n",
+ " <td>_</td>\n",
" </tr>\n",
" <tr>\n",
" <th>132</th>\n",
" <td>CORRECT</td>\n",
- " <td>to</td>\n",
- " <td>to</td>\n",
+ " <td>_</td>\n",
+ " <td>_</td>\n",
" </tr>\n",
" <tr>\n",
" <th>133</th>\n",
" <td>CORRECT</td>\n",
- " <td>przy</td>\n",
- " <td>przy</td>\n",
+ " <td>_</td>\n",
+ " <td>_</td>\n",
" </tr>\n",
" <tr>\n",
" <th>134</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>Sielce</td>\n",
- " <td>sielce</td>\n",
+ " <td>CORRECT</td>\n",
+ " <td>_</td>\n",
+ " <td>_</td>\n",
" </tr>\n",
" <tr>\n",
" <th>135</th>\n",
" <td>CORRECT</td>\n",
- " <td>trza</td>\n",
- " <td>trza</td>\n",
+ " <td>time</td>\n",
+ " <td>time</td>\n",
" </tr>\n",
" <tr>\n",
" <th>136</th>\n",
" <td>CORRECT</td>\n",
- " <td>wysiąść</td>\n",
- " <td>wysiąść</td>\n",
+ " <td>time</td>\n",
+ " <td>time</td>\n",
" </tr>\n",
" <tr>\n",
" <th>137</th>\n",
" <td>CORRECT</td>\n",
- " <td>przy</td>\n",
- " <td>przy</td>\n",
+ " <td>time</td>\n",
+ " <td>time</td>\n",
" </tr>\n",
" <tr>\n",
" <th>138</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>Sielce</td>\n",
- " <td>sielce</td>\n",
+ " <td>CORRECT</td>\n",
+ " <td>time</td>\n",
+ " <td>time</td>\n",
" </tr>\n",
" <tr>\n",
" <th>139</th>\n",
- " <td>CORRECT</td>\n",
- " <td>tak</td>\n",
- " <td>tak</td>\n",
+ " <td>DELETION</td>\n",
+ " <td>_</td>\n",
+ " <td></td>\n",
" </tr>\n",
" <tr>\n",
" <th>140</th>\n",
" <td>DELETION</td>\n",
- " <td>?</td>\n",
+ " <td>_</td>\n",
" <td></td>\n",
" </tr>\n",
" <tr>\n",
" <th>141</th>\n",
- " <td>CORRECT</td>\n",
- " <td>tak</td>\n",
- " <td>tak</td>\n",
+ " <td>DELETION</td>\n",
+ " <td>_</td>\n",
+ " <td></td>\n",
" </tr>\n",
" <tr>\n",
" <th>142</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>przystanek</td>\n",
- " <td>stanek</td>\n",
+ " <td>DELETION</td>\n",
+ " <td>_</td>\n",
+ " <td></td>\n",
" </tr>\n",
" <tr>\n",
" <th>143</th>\n",
" <td>SUBSTITUTION</td>\n",
- " <td>Sielce</td>\n",
- " <td>sielce</td>\n",
+ " <td>_</td>\n",
+ " <td>time</td>\n",
" </tr>\n",
" <tr>\n",
" <th>144</th>\n",
" <td>CORRECT</td>\n",
- " <td>aha</td>\n",
- " <td>aha</td>\n",
+ " <td>_</td>\n",
+ " <td>_</td>\n",
" </tr>\n",
" <tr>\n",
" <th>145</th>\n",
- " <td>DELETION</td>\n",
- " <td>tak</td>\n",
- " <td></td>\n",
+ " <td>CORRECT</td>\n",
+ " <td>_</td>\n",
+ " <td>_</td>\n",
" </tr>\n",
" <tr>\n",
" <th>146</th>\n",
" <td>CORRECT</td>\n",
- " <td>no</td>\n",
- " <td>no</td>\n",
+ " <td>_</td>\n",
+ " <td>_</td>\n",
" </tr>\n",
" <tr>\n",
" <th>147</th>\n",
" <td>CORRECT</td>\n",
- " <td>dobrze</td>\n",
- " <td>dobrze</td>\n",
+ " <td>_</td>\n",
+ " <td>_</td>\n",
" </tr>\n",
" <tr>\n",
" <th>148</th>\n",
" <td>CORRECT</td>\n",
- " <td>a</td>\n",
- " <td>a</td>\n",
+ " <td>_</td>\n",
+ " <td>_</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ " step_type reference_word_text hypothesis_word_text\n",
+ "0 DELETION _ \n",
+ "1 DELETION _ \n",
+ "2 DELETION _ \n",
+ "3 DELETION _ \n",
+ "4 DELETION _ \n",
+ "5 CORRECT _ _\n",
+ "6 CORRECT _ _\n",
+ "7 CORRECT _ _\n",
+ "8 CORRECT _ _\n",
+ "9 CORRECT _ _\n",
+ "10 CORRECT _ _\n",
+ "11 CORRECT _ _\n",
+ "12 CORRECT _ _\n",
+ "13 CORRECT _ _\n",
+ "14 CORRECT _ _\n",
+ "15 CORRECT _ _\n",
+ "16 CORRECT _ _\n",
+ "17 CORRECT _ _\n",
+ "18 DELETION geogName \n",
+ "19 DELETION geogName \n",
+ "20 DELETION geogName \n",
+ "21 CORRECT _ _\n",
+ "22 CORRECT _ _\n",
+ "23 DELETION placeName \n",
+ "24 CORRECT _ _\n",
+ "25 CORRECT _ _\n",
+ "26 CORRECT _ _\n",
+ "27 CORRECT _ _\n",
+ "28 CORRECT _ _\n",
+ "29 CORRECT _ _\n",
+ "30 CORRECT _ _\n",
+ "31 CORRECT _ _\n",
+ "32 DELETION orgName \n",
+ "33 CORRECT _ _\n",
+ "34 CORRECT _ _\n",
+ "35 CORRECT _ _\n",
+ "36 CORRECT _ _\n",
+ "37 CORRECT _ _\n",
+ "38 CORRECT _ _\n",
+ "39 CORRECT _ _\n",
+ "40 CORRECT _ _\n",
+ "41 CORRECT _ _\n",
+ "42 CORRECT _ _\n",
+ "43 DELETION geogName \n",
+ "44 DELETION geogName \n",
+ "45 CORRECT _ _\n",
+ "46 CORRECT placeName placeName\n",
+ "47 CORRECT _ _\n",
+ "48 CORRECT _ _\n",
+ "49 CORRECT _ _\n",
+ "50 DELETION placeName \n",
+ "51 CORRECT _ _\n",
+ "52 CORRECT _ _\n",
+ "53 CORRECT _ _\n",
+ "54 CORRECT _ _\n",
+ "55 CORRECT _ _\n",
+ "56 CORRECT _ _\n",
+ "57 DELETION geogName \n",
+ "58 CORRECT _ _\n",
+ "59 CORRECT _ _\n",
+ "60 CORRECT _ _\n",
+ "61 CORRECT _ _\n",
+ "62 CORRECT _ _\n",
+ "63 CORRECT _ _\n",
+ "64 DELETION persName \n",
+ "65 CORRECT _ _\n",
+ "66 CORRECT _ _\n",
+ "67 CORRECT _ _\n",
+ "68 CORRECT _ _\n",
+ "69 CORRECT _ _\n",
+ "70 CORRECT _ _\n",
+ "71 CORRECT _ _\n",
+ "72 CORRECT _ _\n",
+ "73 DELETION geogName \n",
+ "74 DELETION geogName \n",
+ "75 CORRECT _ _\n",
+ "76 CORRECT _ _\n",
+ "77 CORRECT _ _\n",
+ "78 CORRECT placeName placeName\n",
+ "79 DELETION _ \n",
+ "80 DELETION _ \n",
+ "81 DELETION _ \n",
+ "82 DELETION _ \n",
+ "83 CORRECT _ _\n",
+ "84 CORRECT _ _\n",
+ "85 CORRECT _ _\n",
+ "86 SUBSTITUTION _ placeName\n",
+ "87 CORRECT _ _\n",
+ "88 CORRECT _ _\n",
+ "89 CORRECT _ _\n",
+ "90 DELETION geogName \n",
+ "91 DELETION geogName \n",
+ "92 CORRECT _ _\n",
+ "93 CORRECT _ _\n",
+ "94 CORRECT _ _\n",
+ "95 CORRECT _ _\n",
+ "96 DELETION orgName \n",
+ "97 DELETION orgName \n",
+ "98 CORRECT _ _\n",
+ "99 CORRECT _ _\n",
+ "100 CORRECT _ _\n",
+ "101 CORRECT _ _\n",
+ "102 CORRECT _ _\n",
+ "103 CORRECT _ _\n",
+ "104 CORRECT _ _\n",
+ "105 CORRECT _ _\n",
+ "106 CORRECT _ _\n",
+ "107 CORRECT _ _\n",
+ "108 CORRECT _ _\n",
+ "109 CORRECT _ _\n",
+ "110 CORRECT _ _\n",
+ "111 CORRECT _ _\n",
+ "112 CORRECT _ _\n",
+ "113 CORRECT _ _\n",
+ "114 CORRECT _ _\n",
+ "115 CORRECT _ _\n",
+ "116 CORRECT _ _\n",
+ "117 DELETION placeName \n",
+ "118 DELETION placeName \n",
+ "119 CORRECT _ _\n",
+ "120 CORRECT _ _\n",
+ "121 CORRECT _ _\n",
+ "122 CORRECT _ _\n",
+ "123 CORRECT _ _\n",
+ "124 CORRECT _ _\n",
+ "125 CORRECT _ _\n",
+ "126 CORRECT _ _\n",
+ "127 CORRECT _ _\n",
+ "128 CORRECT _ _\n",
+ "129 DELETION geogName \n",
+ "130 CORRECT _ _\n",
+ "131 CORRECT _ _\n",
+ "132 CORRECT _ _\n",
+ "133 CORRECT _ _\n",
+ "134 CORRECT _ _\n",
+ "135 CORRECT time time\n",
+ "136 CORRECT time time\n",
+ "137 CORRECT time time\n",
+ "138 CORRECT time time\n",
+ "139 DELETION _ \n",
+ "140 DELETION _ \n",
+ "141 DELETION _ \n",
+ "142 DELETION _ \n",
+ "143 SUBSTITUTION _ time\n",
+ "144 CORRECT _ _\n",
+ "145 CORRECT _ _\n",
+ "146 CORRECT _ _\n",
+ "147 CORRECT _ _\n",
+ "148 CORRECT _ _"
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "--------------------------------------------------------------\n",
+ "--------------------------------------------------------------\n",
+ "--------------------------------------------------------------\n"
+ ]
+ }
+ ],
+ "source": [
+ "for it in list(luna_record_provider.get_all_records())[:1]:\n",
+ " show_report_for(it, luna_experiment_repository, techmo_connections_config)"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "id": "a4b4f1bc-f0b3-4d23-bf1d-97f75715f332",
+ "metadata": {},
+ "source": [
+ "# Report for LUNA and AJN ASR"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 25,
+ "id": "27797bad-c92a-45a6-87f2-071645c18150",
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "record_id: LUNA.PL__PRZYSTANKI__DOBRAJAKOSC__M__1_2007-03-30_14_37_38__1_2007-03-30_14_37_38\n",
+ "properties_confiog: AJN ASR\n",
+ "\n",
+ "gold transcript: xxx dzień dobry dzień dobry proszę pana ja mam o której będzie sto czterdzieści trzy będzie najbliższy z Alei Alei Witosa w stronę Gocławia z tego przystanku vis-a-vis ZUSu tak ? no nie nie tam vis-a-vis Panoramy przez Siekierkowski tam w stronę Gocławia ale to nie z tego przystanku Aleja Witosa ? no to jest czy Bartoszka na żądanie wie pan gdzie jest się zaczyna Most Siekierkowski tam w stronę Gocławia gdzie ma on przystanek pierwszy sto czterdzieści trzy znaczy tak naprawdę Most Siekierkowski to się zaczyna za Siekierki Sanktuarium no właśnie przed tym przed tym przystanek o której jest sto czterdzieści trzy najbliższy aha czyli to wtedy przystanek Małe Siekierki ale to nie jest tak tak tak tak na wysokości Panoramy aha dobrze najbliższy już chwileczkę czternasta czterdzieści sześć piętnasta zero jeden aha no dobrze dziękuję do widzenia do widzenia\n",
+ "\n",
+ "asr transcript: dobre dyrektor proszę wybaczyć tryb numer jeden to teresie trzeba będzie najbliższy ale i tu aleje pić od roztropnego działania swego przystankom vis-a-vis zus-u to jak mnie nie <unk> widać <unk> panoramę przez siekierko trwałego tonę antoniego przystanki kolejowe to było coś czy bartoszka na żądanie <unk> <unk> <unk> wielbłądy się toczy na most siekierkowski to trud i czytanek pieszczoty się trzy płaczesz tak naprawdę może kierkowski to zaczną siekierki sanktuarium w lourdes się tym przejęty przystanku który torresie czne edition - czyli to wspólny przystanek małe siekierki ale to nie do końca dotrzymać dziś są czternastej czterdzieści sześć piętnasto żeruje a nowy gen. \n",
+ "\n",
+ "word wer {'classic_wer': 0.8297872340425532}\n",
+ "\n",
+ "pos wer {'classic_wer': 0.6778523489932886}\n",
+ "\n",
+ "tag wer {'classic_wer': 0.8456375838926175}\n",
+ "\n",
+ "ner wer {'classic_wer': 0.22818791946308725}\n",
+ "\n"
+ ]
+ },
+ {
+ "data": {
+ "text/html": [
+ "<div>\n",
+ "<style scoped>\n",
+ " .dataframe tbody tr th:only-of-type {\n",
+ " vertical-align: middle;\n",
+ " }\n",
+ "\n",
+ " .dataframe tbody tr th {\n",
+ " vertical-align: top;\n",
+ " }\n",
+ "\n",
+ " .dataframe thead th {\n",
+ " text-align: right;\n",
+ " }\n",
+ "</style>\n",
+ "<table border=\"1\" class=\"dataframe\">\n",
+ " <thead>\n",
+ " <tr style=\"text-align: right;\">\n",
+ " <th></th>\n",
+ " <th>step_type</th>\n",
+ " <th>reference_word_text</th>\n",
+ " <th>hypothesis_word_text</th>\n",
" </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
" <tr>\n",
- " <th>149</th>\n",
+ " <th>0</th>\n",
" <td>DELETION</td>\n",
- " <td>Sielce</td>\n",
+ " <td>xxx</td>\n",
" <td></td>\n",
" </tr>\n",
" <tr>\n",
- " <th>150</th>\n",
+ " <th>1</th>\n",
" <td>DELETION</td>\n",
- " <td>to</td>\n",
+ " <td>dzień</td>\n",
" <td></td>\n",
" </tr>\n",
" <tr>\n",
- " <th>151</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>znaczy</td>\n",
- " <td>sielce</td>\n",
+ " <th>2</th>\n",
+ " <td>DELETION</td>\n",
+ " <td>dobry</td>\n",
+ " <td></td>\n",
" </tr>\n",
" <tr>\n",
- " <th>152</th>\n",
- " <td>CORRECT</td>\n",
- " <td>jaka</td>\n",
- " <td>jaka</td>\n",
+ " <th>3</th>\n",
+ " <td>SUBSTITUTION</td>\n",
+ " <td>dzień</td>\n",
+ " <td>dobre</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>153</th>\n",
- " <td>CORRECT</td>\n",
- " <td>to</td>\n",
- " <td>to</td>\n",
+ " <th>4</th>\n",
+ " <td>SUBSTITUTION</td>\n",
+ " <td>dobry</td>\n",
+ " <td>dyrektor</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>154</th>\n",
+ " <th>5</th>\n",
" <td>CORRECT</td>\n",
- " <td>już</td>\n",
- " <td>już</td>\n",
+ " <td>proszÄ™</td>\n",
+ " <td>proszÄ™</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>155</th>\n",
- " <td>CORRECT</td>\n",
- " <td>jest</td>\n",
- " <td>jest</td>\n",
+ " <th>6</th>\n",
+ " <td>DELETION</td>\n",
+ " <td>pana</td>\n",
+ " <td></td>\n",
" </tr>\n",
" <tr>\n",
- " <th>156</th>\n",
- " <td>CORRECT</td>\n",
- " <td>dzielnica</td>\n",
- " <td>dzielnica</td>\n",
+ " <th>7</th>\n",
+ " <td>DELETION</td>\n",
+ " <td>ja</td>\n",
+ " <td></td>\n",
" </tr>\n",
" <tr>\n",
- " <th>157</th>\n",
- " <td>CORRECT</td>\n",
- " <td>to</td>\n",
- " <td>to</td>\n",
+ " <th>8</th>\n",
+ " <td>SUBSTITUTION</td>\n",
+ " <td>mam</td>\n",
+ " <td>wybaczyć</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>158</th>\n",
- " <td>CORRECT</td>\n",
- " <td>ta</td>\n",
- " <td>ta</td>\n",
+ " <th>9</th>\n",
+ " <td>SUBSTITUTION</td>\n",
+ " <td>o</td>\n",
+ " <td>tryb</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>159</th>\n",
- " <td>CORRECT</td>\n",
- " <td>jest</td>\n",
- " <td>jest</td>\n",
+ " <th>10</th>\n",
+ " <td>SUBSTITUTION</td>\n",
+ " <td>której</td>\n",
+ " <td>numer</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>160</th>\n",
- " <td>CORRECT</td>\n",
- " <td>przy</td>\n",
- " <td>przy</td>\n",
+ " <th>11</th>\n",
+ " <td>SUBSTITUTION</td>\n",
+ " <td>będzie</td>\n",
+ " <td>jeden</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>161</th>\n",
- " <td>CORRECT</td>\n",
- " <td>ulica</td>\n",
- " <td>ulica</td>\n",
+ " <th>12</th>\n",
+ " <td>SUBSTITUTION</td>\n",
+ " <td>sto</td>\n",
+ " <td>to</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>162</th>\n",
+ " <th>13</th>\n",
" <td>SUBSTITUTION</td>\n",
- " <td>Gagarina</td>\n",
- " <td>gagarina</td>\n",
+ " <td>czterdzieści</td>\n",
+ " <td>teresie</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>163</th>\n",
- " <td>CORRECT</td>\n",
- " <td>a</td>\n",
- " <td>a</td>\n",
+ " <th>14</th>\n",
+ " <td>SUBSTITUTION</td>\n",
+ " <td>trzy</td>\n",
+ " <td>trzeba</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>164</th>\n",
+ " <th>15</th>\n",
" <td>CORRECT</td>\n",
- " <td>przy</td>\n",
- " <td>przy</td>\n",
+ " <td>będzie</td>\n",
+ " <td>będzie</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>165</th>\n",
+ " <th>16</th>\n",
" <td>CORRECT</td>\n",
- " <td>ulicy</td>\n",
- " <td>ulicy</td>\n",
+ " <td>najbliższy</td>\n",
+ " <td>najbliższy</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>166</th>\n",
+ " <th>17</th>\n",
" <td>SUBSTITUTION</td>\n",
- " <td>Gagarina</td>\n",
- " <td>gagarina</td>\n",
+ " <td>z</td>\n",
+ " <td>ale</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>167</th>\n",
- " <td>CORRECT</td>\n",
- " <td>czyli</td>\n",
- " <td>czyli</td>\n",
+ " <th>18</th>\n",
+ " <td>SUBSTITUTION</td>\n",
+ " <td>Alei</td>\n",
+ " <td>i</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>168</th>\n",
- " <td>CORRECT</td>\n",
- " <td>to</td>\n",
- " <td>to</td>\n",
+ " <th>19</th>\n",
+ " <td>SUBSTITUTION</td>\n",
+ " <td>Alei</td>\n",
+ " <td>tu</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>169</th>\n",
- " <td>CORRECT</td>\n",
- " <td>jest</td>\n",
- " <td>jest</td>\n",
+ " <th>20</th>\n",
+ " <td>SUBSTITUTION</td>\n",
+ " <td>Witosa</td>\n",
+ " <td>aleje</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>170</th>\n",
- " <td>CORRECT</td>\n",
- " <td>tam</td>\n",
- " <td>tam</td>\n",
+ " <th>21</th>\n",
+ " <td>SUBSTITUTION</td>\n",
+ " <td>w</td>\n",
+ " <td>pić</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>171</th>\n",
+ " <th>22</th>\n",
" <td>SUBSTITUTION</td>\n",
- " <td>Mokotów</td>\n",
- " <td>mokotów</td>\n",
+ " <td>stronÄ™</td>\n",
+ " <td>od</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>172</th>\n",
- " <td>CORRECT</td>\n",
- " <td>po</td>\n",
- " <td>po</td>\n",
+ " <th>23</th>\n",
+ " <td>SUBSTITUTION</td>\n",
+ " <td>Gocławia</td>\n",
+ " <td>roztropnego</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>173</th>\n",
- " <td>CORRECT</td>\n",
- " <td>prostu</td>\n",
- " <td>prostu</td>\n",
+ " <th>24</th>\n",
+ " <td>SUBSTITUTION</td>\n",
+ " <td>z</td>\n",
+ " <td>działania</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>174</th>\n",
- " <td>CORRECT</td>\n",
- " <td>tak</td>\n",
- " <td>tak</td>\n",
+ " <th>25</th>\n",
+ " <td>SUBSTITUTION</td>\n",
+ " <td>tego</td>\n",
+ " <td>swego</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>175</th>\n",
- " <td>DELETION</td>\n",
- " <td>?</td>\n",
- " <td></td>\n",
+ " <th>26</th>\n",
+ " <td>SUBSTITUTION</td>\n",
+ " <td>przystanku</td>\n",
+ " <td>przystankom</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>176</th>\n",
+ " <th>27</th>\n",
" <td>CORRECT</td>\n",
- " <td>tak</td>\n",
- " <td>tak</td>\n",
+ " <td>vis-a-vis</td>\n",
+ " <td>vis-a-vis</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>177</th>\n",
+ " <th>28</th>\n",
" <td>SUBSTITUTION</td>\n",
- " <td>Siekierki</td>\n",
- " <td>siekierki</td>\n",
+ " <td>ZUSu</td>\n",
+ " <td>zus-u</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>178</th>\n",
+ " <th>29</th>\n",
" <td>SUBSTITUTION</td>\n",
- " <td>Mokotów</td>\n",
- " <td>mokot</td>\n",
+ " <td>tak</td>\n",
+ " <td>to</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>179</th>\n",
+ " <th>30</th>\n",
" <td>SUBSTITUTION</td>\n",
- " <td>a</td>\n",
- " <td>siekierki</td>\n",
+ " <td>?</td>\n",
+ " <td>jak</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>180</th>\n",
+ " <th>31</th>\n",
" <td>SUBSTITUTION</td>\n",
- " <td>Siekierki</td>\n",
- " <td>mokot</td>\n",
+ " <td>no</td>\n",
+ " <td>mnie</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>181</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>Mokotów</td>\n",
- " <td>ów</td>\n",
+ " <th>32</th>\n",
+ " <td>CORRECT</td>\n",
+ " <td>nie</td>\n",
+ " <td>nie</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>182</th>\n",
- " <td>CORRECT</td>\n",
- " <td>i</td>\n",
- " <td>i</td>\n",
+ " <th>33</th>\n",
+ " <td>SUBSTITUTION</td>\n",
+ " <td>nie</td>\n",
+ " <td><unk></td>\n",
" </tr>\n",
" <tr>\n",
- " <th>183</th>\n",
- " <td>CORRECT</td>\n",
- " <td>tam</td>\n",
+ " <th>34</th>\n",
+ " <td>SUBSTITUTION</td>\n",
" <td>tam</td>\n",
+ " <td>widać</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>184</th>\n",
- " <td>CORRECT</td>\n",
- " <td>jak</td>\n",
- " <td>jak</td>\n",
+ " <th>35</th>\n",
+ " <td>SUBSTITUTION</td>\n",
+ " <td>vis-a-vis</td>\n",
+ " <td><unk></td>\n",
" </tr>\n",
" <tr>\n",
- " <th>185</th>\n",
- " <td>CORRECT</td>\n",
- " <td>pani</td>\n",
- " <td>pani</td>\n",
+ " <th>36</th>\n",
+ " <td>SUBSTITUTION</td>\n",
+ " <td>Panoramy</td>\n",
+ " <td>panoramÄ™</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>186</th>\n",
+ " <th>37</th>\n",
" <td>CORRECT</td>\n",
- " <td>wysiÄ…dzie</td>\n",
- " <td>wysiÄ…dzie</td>\n",
+ " <td>przez</td>\n",
+ " <td>przez</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>187</th>\n",
- " <td>CORRECT</td>\n",
- " <td>to</td>\n",
- " <td>to</td>\n",
+ " <th>38</th>\n",
+ " <td>SUBSTITUTION</td>\n",
+ " <td>Siekierkowski</td>\n",
+ " <td>siekierko</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>188</th>\n",
- " <td>CORRECT</td>\n",
- " <td>trza</td>\n",
- " <td>trza</td>\n",
+ " <th>39</th>\n",
+ " <td>SUBSTITUTION</td>\n",
+ " <td>tam</td>\n",
+ " <td>trwałego</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>189</th>\n",
- " <td>CORRECT</td>\n",
- " <td>wejść</td>\n",
- " <td>wejść</td>\n",
+ " <th>40</th>\n",
+ " <td>SUBSTITUTION</td>\n",
+ " <td>w</td>\n",
+ " <td>tonÄ™</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>190</th>\n",
- " <td>DELETION</td>\n",
- " <td>w</td>\n",
- " <td></td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>191</th>\n",
- " <td>DELETION</td>\n",
- " <td>lewo</td>\n",
- " <td></td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>192</th>\n",
- " <td>DELETION</td>\n",
- " <td>w</td>\n",
- " <td></td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>193</th>\n",
- " <td>DELETION</td>\n",
- " <td>ulicÄ™</td>\n",
- " <td></td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>194</th>\n",
+ " <th>41</th>\n",
" <td>SUBSTITUTION</td>\n",
- " <td>Nehru</td>\n",
- " <td>scenerii</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>195</th>\n",
- " <td>CORRECT</td>\n",
- " <td>i</td>\n",
- " <td>i</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>196</th>\n",
- " <td>CORRECT</td>\n",
- " <td>od</td>\n",
- " <td>od</td>\n",
+ " <td>stronÄ™</td>\n",
+ " <td>antoniego</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>197</th>\n",
+ " <th>42</th>\n",
" <td>SUBSTITUTION</td>\n",
- " <td>Nehru</td>\n",
- " <td>nehru</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>198</th>\n",
- " <td>CORRECT</td>\n",
- " <td>odchodzi</td>\n",
- " <td>odchodzi</td>\n",
+ " <td>Gocławia</td>\n",
+ " <td>przystanki</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>199</th>\n",
+ " <th>43</th>\n",
" <td>SUBSTITUTION</td>\n",
- " <td>Zwierzyniecka</td>\n",
- " <td>zwierzyniecka</td>\n",
+ " <td>ale</td>\n",
+ " <td>kolejowe</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>200</th>\n",
+ " <th>44</th>\n",
" <td>CORRECT</td>\n",
- " <td>w</td>\n",
- " <td>w</td>\n",
+ " <td>to</td>\n",
+ " <td>to</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>201</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>lewo</td>\n",
- " <td>le</td>\n",
+ " <th>45</th>\n",
+ " <td>DELETION</td>\n",
+ " <td>nie</td>\n",
+ " <td></td>\n",
" </tr>\n",
" <tr>\n",
- " <th>202</th>\n",
- " <td>CORRECT</td>\n",
- " <td>w</td>\n",
- " <td>w</td>\n",
+ " <th>46</th>\n",
+ " <td>DELETION</td>\n",
+ " <td>z</td>\n",
+ " <td></td>\n",
" </tr>\n",
" <tr>\n",
- " <th>203</th>\n",
- " <td>CORRECT</td>\n",
- " <td>lewo</td>\n",
- " <td>lewo</td>\n",
+ " <th>47</th>\n",
+ " <td>DELETION</td>\n",
+ " <td>tego</td>\n",
+ " <td></td>\n",
" </tr>\n",
" <tr>\n",
- " <th>204</th>\n",
- " <td>CORRECT</td>\n",
- " <td>i</td>\n",
- " <td>i</td>\n",
+ " <th>48</th>\n",
+ " <td>DELETION</td>\n",
+ " <td>przystanku</td>\n",
+ " <td></td>\n",
" </tr>\n",
" <tr>\n",
- " <th>205</th>\n",
- " <td>CORRECT</td>\n",
- " <td>ulica</td>\n",
- " <td>ulica</td>\n",
+ " <th>49</th>\n",
+ " <td>DELETION</td>\n",
+ " <td>Aleja</td>\n",
+ " <td></td>\n",
" </tr>\n",
" <tr>\n",
- " <th>206</th>\n",
+ " <th>50</th>\n",
" <td>DELETION</td>\n",
- " <td>Nehru</td>\n",
+ " <td>Witosa</td>\n",
" <td></td>\n",
" </tr>\n",
" <tr>\n",
- " <th>207</th>\n",
- " <td>SUBSTITUTION</td>\n",
+ " <th>51</th>\n",
+ " <td>DELETION</td>\n",
" <td>?</td>\n",
- " <td>nehru</td>\n",
+ " <td></td>\n",
" </tr>\n",
" <tr>\n",
- " <th>208</th>\n",
- " <td>CORRECT</td>\n",
- " <td>tak</td>\n",
- " <td>tak</td>\n",
+ " <th>52</th>\n",
+ " <td>DELETION</td>\n",
+ " <td>no</td>\n",
+ " <td></td>\n",
" </tr>\n",
" <tr>\n",
- " <th>209</th>\n",
+ " <th>53</th>\n",
" <td>SUBSTITUTION</td>\n",
- " <td>Nehru</td>\n",
- " <td>nehru</td>\n",
+ " <td>to</td>\n",
+ " <td>było</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>210</th>\n",
- " <td>CORRECT</td>\n",
- " <td>dobrze</td>\n",
- " <td>dobrze</td>\n",
+ " <th>54</th>\n",
+ " <td>SUBSTITUTION</td>\n",
+ " <td>jest</td>\n",
+ " <td>coÅ›</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>211</th>\n",
+ " <th>55</th>\n",
" <td>CORRECT</td>\n",
- " <td>dziękuję</td>\n",
- " <td>dziękuję</td>\n",
+ " <td>czy</td>\n",
+ " <td>czy</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>212</th>\n",
- " <td>CORRECT</td>\n",
- " <td>panu</td>\n",
- " <td>panu</td>\n",
+ " <th>56</th>\n",
+ " <td>SUBSTITUTION</td>\n",
+ " <td>Bartoszka</td>\n",
+ " <td>bartoszka</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>213</th>\n",
+ " <th>57</th>\n",
" <td>CORRECT</td>\n",
- " <td>bardzo</td>\n",
- " <td>bardzo</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>214</th>\n",
- " <td>DELETION</td>\n",
- " <td>proszÄ™</td>\n",
- " <td></td>\n",
+ " <td>na</td>\n",
+ " <td>na</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>215</th>\n",
+ " <th>58</th>\n",
" <td>CORRECT</td>\n",
- " <td>do</td>\n",
- " <td>do</td>\n",
+ " <td>żądanie</td>\n",
+ " <td>żądanie</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>216</th>\n",
- " <td>CORRECT</td>\n",
- " <td>widzenia</td>\n",
- " <td>widzenia</td>\n",
+ " <th>59</th>\n",
+ " <td>SUBSTITUTION</td>\n",
+ " <td>wie</td>\n",
+ " <td><unk></td>\n",
" </tr>\n",
" <tr>\n",
- " <th>217</th>\n",
+ " <th>60</th>\n",
" <td>SUBSTITUTION</td>\n",
- " <td>do</td>\n",
- " <td>to</td>\n",
+ " <td>pan</td>\n",
+ " <td><unk></td>\n",
" </tr>\n",
" <tr>\n",
- " <th>218</th>\n",
+ " <th>61</th>\n",
" <td>SUBSTITUTION</td>\n",
- " <td>widzenia</td>\n",
- " <td>wszystko</td>\n",
+ " <td>gdzie</td>\n",
+ " <td><unk></td>\n",
" </tr>\n",
- " </tbody>\n",
- "</table>\n",
- "</div>"
- ],
- "text/plain": [
- " step_type reference_word_text hypothesis_word_text\n",
- "0 DELETION xxx \n",
- "1 CORRECT dzień dzień\n",
- "2 CORRECT dobry dobry\n",
- "3 CORRECT dzień dzień\n",
- "4 CORRECT dobry dobry\n",
- "5 CORRECT proszÄ™ proszÄ™\n",
- "6 CORRECT pana pana\n",
- "7 CORRECT ja ja\n",
- "8 CORRECT chciałam chciałam\n",
- "9 CORRECT siÄ™ siÄ™\n",
- "10 CORRECT dowiedzieć dowiedzieć\n",
- "11 CORRECT bo bo\n",
- "12 CORRECT nie nie\n",
- "13 CORRECT bardzo bardzo\n",
- "14 CORRECT wiem wiem\n",
- "15 CORRECT gdzie gdzie\n",
- "16 CORRECT znajduje znajduje\n",
- "17 CORRECT siÄ™ siÄ™\n",
- "18 CORRECT ulica ulica\n",
- "19 SUBSTITUTION Zwierzyniecka zwierzyniecka\n",
- "20 CORRECT i i\n",
- "21 CORRECT jak jak\n",
- "22 CORRECT dojechać dojechać\n",
- "23 CORRECT z z\n",
- "24 DELETION Bródna \n",
- "25 DELETION na \n",
- "26 DELETION przykład \n",
- "27 SUBSTITUTION ? bródna\n",
- "28 CORRECT na na\n",
- "29 SUBSTITUTION ZwierzynieckÄ… zwierzynieckÄ…\n",
- "30 CORRECT na na\n",
- "31 SUBSTITUTION ZwierzynieckÄ… zwierzynieckÄ…\n",
- "32 SUBSTITUTION a ja\n",
- "33 CORRECT z z\n",
- "34 SUBSTITUTION Bródna bródna\n",
- "35 CORRECT z z\n",
- "36 CORRECT którego którego\n",
- "37 CORRECT miejsca miejsca\n",
- "38 DELETION ? \n",
- "39 CORRECT z z\n",
- "40 SUBSTITUTION Bródna bródna\n",
- "41 CORRECT to to\n",
- "42 CORRECT jest jest\n",
- "43 CORRECT ulica ulica\n",
- "44 SUBSTITUTION Wyszogrodzka wyszogrodzka\n",
- "45 CORRECT tu tu\n",
- "46 CORRECT przy przy\n",
- "47 SUBSTITUTION Rembielińskiej rembielińskiej\n",
- "48 CORRECT czyli czyli\n",
- "49 CORRECT przy przy\n",
- "50 CORRECT tramwajach tramwajach\n",
- "51 DELETION tak \n",
- "52 DELETION ? \n",
- "53 CORRECT przy przy\n",
- "54 CORRECT tramwajach tramwajach\n",
- "55 CORRECT tak tak\n",
- "56 CORRECT może może\n",
- "57 DELETION pani \n",
- "58 DELETION poczeka \n",
- "59 CORRECT sprawdzÄ™ sprawdzÄ™\n",
- "60 CORRECT dobrze dobrze\n",
- "61 CORRECT dobrze dobrze\n",
- "62 DELETION pani \n",
- "63 DELETION sobie \n",
- "64 CORRECT podjedzie podjedzie\n",
- "65 CORRECT tramwajem tramwajem\n",
- "66 CORRECT do do\n",
- "67 SUBSTITUTION Ronda ronda\n",
- "68 SUBSTITUTION Żaba żaba\n",
- "69 CORRECT tak tak\n",
- "70 CORRECT od od\n",
- "71 SUBSTITUTION Ronda ronda\n",
- "72 SUBSTITUTION Żaba żaba\n",
- "73 CORRECT już już\n",
- "74 DELETION sto \n",
- "75 DELETION sześćdziesiąt \n",
- "76 SUBSTITUTION dwa 162\n",
- "77 CORRECT jest jest\n",
- "78 DELETION sto \n",
- "79 DELETION sześćdziesiąt \n",
- "80 SUBSTITUTION dwa 162\n",
- "81 CORRECT tak tak\n",
- "82 CORRECT i i\n",
- "83 DELETION sto \n",
- "84 DELETION sześćdziesiąt \n",
- "85 SUBSTITUTION dwa 162\n",
- "86 CORRECT tam tam\n",
- "87 CORRECT dojadÄ™ dojadÄ™\n",
- "88 CORRECT do do\n",
- "89 CORRECT tej tej\n",
- "90 SUBSTITUTION ulicy uli\n",
- "91 CORRECT tak tak\n",
- "92 CORRECT może może\n",
- "93 CORRECT pani pani\n",
- "94 CORRECT wysiąść wysiąść\n",
- "95 DELETION na \n",
- "96 SUBSTITUTION przystanku banku\n",
- "97 SUBSTITUTION Bartycka bartycka\n",
- "98 CORRECT albo albo\n",
- "99 SUBSTITUTION Sielce sielce\n",
- "100 SUBSTITUTION Bartycka bartycka\n",
- "101 CORRECT albo albo\n",
- "102 DELETION ? \n",
- "103 SUBSTITUTION Sielce sielce\n",
- "104 SUBSTITUTION Sielce sielce\n",
- "105 CORRECT tak tak\n",
- "106 DELETION ? \n",
- "107 CORRECT tak tak\n",
- "108 CORRECT aha aha\n",
- "109 CORRECT i i\n",
- "110 CORRECT tam tam\n",
- "111 CORRECT w w\n",
- "112 CORRECT pobliżu pobliżu\n",
- "113 CORRECT jest jest\n",
- "114 CORRECT ta ta\n",
- "115 CORRECT ulica ulica\n",
- "116 DELETION tak \n",
- "117 DELETION ? \n",
- "118 DELETION a \n",
- "119 DELETION Zwierzyniecka \n",
- "120 DELETION wysoki \n",
- "121 SUBSTITUTION numer zwierzyniecka\n",
- "122 CORRECT ma ma\n",
- "123 CORRECT pani pani\n",
- "124 SUBSTITUTION ? zwierzyniecka\n",
- "125 SUBSTITUTION Zwierzyniecka telefonem\n",
- "126 SUBSTITUTION zaraz dzikie\n",
- "127 SUBSTITUTION momencik który\n",
- "128 SUBSTITUTION osiem 8\n",
- "129 SUBSTITUTION A a\n",
- "130 SUBSTITUTION Zwierzyniecka zwierzyniecka\n",
- "131 CORRECT to to\n",
- "132 CORRECT to to\n",
- "133 CORRECT przy przy\n",
- "134 SUBSTITUTION Sielce sielce\n",
- "135 CORRECT trza trza\n",
- "136 CORRECT wysiąść wysiąść\n",
- "137 CORRECT przy przy\n",
- "138 SUBSTITUTION Sielce sielce\n",
- "139 CORRECT tak tak\n",
- "140 DELETION ? \n",
- "141 CORRECT tak tak\n",
- "142 SUBSTITUTION przystanek stanek\n",
- "143 SUBSTITUTION Sielce sielce\n",
- "144 CORRECT aha aha\n",
- "145 DELETION tak \n",
- "146 CORRECT no no\n",
- "147 CORRECT dobrze dobrze\n",
- "148 CORRECT a a\n",
- "149 DELETION Sielce \n",
- "150 DELETION to \n",
- "151 SUBSTITUTION znaczy sielce\n",
- "152 CORRECT jaka jaka\n",
- "153 CORRECT to to\n",
- "154 CORRECT już już\n",
- "155 CORRECT jest jest\n",
- "156 CORRECT dzielnica dzielnica\n",
- "157 CORRECT to to\n",
- "158 CORRECT ta ta\n",
- "159 CORRECT jest jest\n",
- "160 CORRECT przy przy\n",
- "161 CORRECT ulica ulica\n",
- "162 SUBSTITUTION Gagarina gagarina\n",
- "163 CORRECT a a\n",
- "164 CORRECT przy przy\n",
- "165 CORRECT ulicy ulicy\n",
- "166 SUBSTITUTION Gagarina gagarina\n",
- "167 CORRECT czyli czyli\n",
- "168 CORRECT to to\n",
- "169 CORRECT jest jest\n",
- "170 CORRECT tam tam\n",
- "171 SUBSTITUTION Mokotów mokotów\n",
- "172 CORRECT po po\n",
- "173 CORRECT prostu prostu\n",
- "174 CORRECT tak tak\n",
- "175 DELETION ? \n",
- "176 CORRECT tak tak\n",
- "177 SUBSTITUTION Siekierki siekierki\n",
- "178 SUBSTITUTION Mokotów mokot\n",
- "179 SUBSTITUTION a siekierki\n",
- "180 SUBSTITUTION Siekierki mokot\n",
- "181 SUBSTITUTION Mokotów ów\n",
- "182 CORRECT i i\n",
- "183 CORRECT tam tam\n",
- "184 CORRECT jak jak\n",
- "185 CORRECT pani pani\n",
- "186 CORRECT wysiÄ…dzie wysiÄ…dzie\n",
- "187 CORRECT to to\n",
- "188 CORRECT trza trza\n",
- "189 CORRECT wejść wejść\n",
- "190 DELETION w \n",
- "191 DELETION lewo \n",
- "192 DELETION w \n",
- "193 DELETION ulicÄ™ \n",
- "194 SUBSTITUTION Nehru scenerii\n",
- "195 CORRECT i i\n",
- "196 CORRECT od od\n",
- "197 SUBSTITUTION Nehru nehru\n",
- "198 CORRECT odchodzi odchodzi\n",
- "199 SUBSTITUTION Zwierzyniecka zwierzyniecka\n",
- "200 CORRECT w w\n",
- "201 SUBSTITUTION lewo le\n",
- "202 CORRECT w w\n",
- "203 CORRECT lewo lewo\n",
- "204 CORRECT i i\n",
- "205 CORRECT ulica ulica\n",
- "206 DELETION Nehru \n",
- "207 SUBSTITUTION ? nehru\n",
- "208 CORRECT tak tak\n",
- "209 SUBSTITUTION Nehru nehru\n",
- "210 CORRECT dobrze dobrze\n",
- "211 CORRECT dziękuję dziękuję\n",
- "212 CORRECT panu panu\n",
- "213 CORRECT bardzo bardzo\n",
- "214 DELETION proszÄ™ \n",
- "215 CORRECT do do\n",
- "216 CORRECT widzenia widzenia\n",
- "217 SUBSTITUTION do to\n",
- "218 SUBSTITUTION widzenia wszystko"
- ]
- },
- "metadata": {},
- "output_type": "display_data"
- },
- {
- "name": "stdout",
- "output_type": "stream",
- "text": [
- "--------------------------------------------------------------\n",
- "--------------------------------------------------------------\n",
- "--------------------------------------------------------------\n"
- ]
- }
- ],
- "source": [
- "for it in list(luna_record_provider.get_all_records())[:1]:\n",
- " show_report_for(it, luna_experiment_repository, techmo_connections_config)"
- ]
- },
- {
- "cell_type": "markdown",
- "id": "a4b4f1bc-f0b3-4d23-bf1d-97f75715f332",
- "metadata": {},
- "source": [
- "# Report for LUNA and AJN ASR"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 37,
- "id": "27797bad-c92a-45a6-87f2-071645c18150",
- "metadata": {},
- "outputs": [
- {
- "name": "stdout",
- "output_type": "stream",
- "text": [
- "record_id: LUNA.PL__JAKDOJECHAC__DOBRAJAKOSC__F__2_2007-03-26_12_22_36__2_2007-03-26_12_22_36\n",
- "properties_confiog: AJN ASR\n",
- "\n",
- "gold transcript: xxx dzień dobry dzień dobry proszę pana ja chciałam się dowiedzieć bo nie bardzo wiem gdzie znajduje się ulica Zwierzyniecka i jak dojechać z Bródna na przykład ? na Zwierzyniecką na Zwierzyniecką a z Bródna z którego miejsca ? z Bródna to jest ulica Wyszogrodzka tu przy Rembielińskiej czyli przy tramwajach tak ? przy tramwajach tak może pani poczeka sprawdzę dobrze dobrze pani sobie podjedzie tramwajem do Ronda Żaba tak od Ronda Żaba już sto sześćdziesiąt dwa jest sto sześćdziesiąt dwa tak i sto sześćdziesiąt dwa tam dojadę do tej ulicy tak może pani wysiąść na przystanku Bartycka albo Sielce Bartycka albo ? Sielce Sielce tak ? tak aha i tam w pobliżu jest ta ulica tak ? a Zwierzyniecka wysoki numer ma pani ? Zwierzyniecka zaraz momencik osiem A Zwierzyniecka to to przy Sielce trza wysiąść przy Sielce tak ? tak przystanek Sielce aha tak no dobrze a Sielce to znaczy jaka to już jest dzielnica to ta jest przy ulica Gagarina a przy ulicy Gagarina czyli to jest tam Mokotów po prostu tak ? tak Siekierki Mokotów a Siekierki Mokotów i tam jak pani wysiądzie to trza wejść w lewo w ulicę Nehru i od Nehru odchodzi Zwierzyniecka w lewo w lewo i ulica Nehru ? tak Nehru dobrze dziękuję panu bardzo proszę do widzenia do widzenia\n",
- "\n",
- "asr transcript: niedobre n. e. pracy a to długo nie było to dziecko czuje się równie szybko jak to cecha brud ta na przykład się ostatnio inżynierowie i brudno straszliwy szok brodatego ulica wyszogrodzka przy rembielińskiej ich cztero oto ta jak tak dużo punktów <unk> oni żeby podróży tramwajem do rondo Żaba <unk> toronto już sto sześćdziesiąt wojsk sto sześćdziesiąt ta <unk> trzysta sześćdziesiąt rataja <unk> tej <unk> może pojawić się trzy stąd <unk> <unk> <unk> <unk> <unk> berty coraz szybciej bartycka <unk> trzema trzeba się trochę tak jak i te plany stały się słynne ciężko dysząc i numer ewidencyjny <unk> nowy typ <unk> - się - dla mnie trwało to trzy trzody ścięte tato taneczne <unk> ta notatka się tutaj także kilka tutaj trzy czy cztery dni <unk> płyty darin nakryta plakatów pod hutach siekierkowską <unk> a siekierki hoszowski czytelnik wyszedł od swoich kolegów uliczek <unk> od <unk> odchodzi służy nie tylko <unk> na ulicach <unk> tak numeru krytykuje pan <unk> badania <unk> \n",
- "\n",
- "word wer {'classic_wer': 0.8858447488584474}\n",
- "\n",
- "pos wer {'classic_wer': 0.7671232876712328}\n",
- "\n",
- "tag wer {'classic_wer': 0.9269406392694064}\n",
- "\n"
- ]
- },
- {
- "data": {
- "text/html": [
- "<div>\n",
- "<style scoped>\n",
- " .dataframe tbody tr th:only-of-type {\n",
- " vertical-align: middle;\n",
- " }\n",
- "\n",
- " .dataframe tbody tr th {\n",
- " vertical-align: top;\n",
- " }\n",
- "\n",
- " .dataframe thead th {\n",
- " text-align: right;\n",
- " }\n",
- "</style>\n",
- "<table border=\"1\" class=\"dataframe\">\n",
- " <thead>\n",
- " <tr style=\"text-align: right;\">\n",
- " <th></th>\n",
- " <th>step_type</th>\n",
- " <th>reference_word_text</th>\n",
- " <th>hypothesis_word_text</th>\n",
+ " <tr>\n",
+ " <th>62</th>\n",
+ " <td>SUBSTITUTION</td>\n",
+ " <td>jest</td>\n",
+ " <td>wielbłądy</td>\n",
" </tr>\n",
- " </thead>\n",
- " <tbody>\n",
" <tr>\n",
- " <th>0</th>\n",
- " <td>DELETION</td>\n",
- " <td>xxx</td>\n",
- " <td></td>\n",
+ " <th>63</th>\n",
+ " <td>CORRECT</td>\n",
+ " <td>siÄ™</td>\n",
+ " <td>siÄ™</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>1</th>\n",
+ " <th>64</th>\n",
" <td>DELETION</td>\n",
- " <td>dzień</td>\n",
+ " <td>zaczyna</td>\n",
" <td></td>\n",
" </tr>\n",
" <tr>\n",
- " <th>2</th>\n",
+ " <th>65</th>\n",
" <td>DELETION</td>\n",
- " <td>dobry</td>\n",
+ " <td>Most</td>\n",
" <td></td>\n",
" </tr>\n",
" <tr>\n",
- " <th>3</th>\n",
+ " <th>66</th>\n",
" <td>DELETION</td>\n",
- " <td>dzień</td>\n",
+ " <td>Siekierkowski</td>\n",
" <td></td>\n",
" </tr>\n",
" <tr>\n",
- " <th>4</th>\n",
+ " <th>67</th>\n",
" <td>DELETION</td>\n",
- " <td>dobry</td>\n",
+ " <td>tam</td>\n",
" <td></td>\n",
" </tr>\n",
" <tr>\n",
- " <th>5</th>\n",
+ " <th>68</th>\n",
" <td>SUBSTITUTION</td>\n",
- " <td>proszÄ™</td>\n",
- " <td>niedobre</td>\n",
+ " <td>w</td>\n",
+ " <td>toczy</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>6</th>\n",
+ " <th>69</th>\n",
" <td>SUBSTITUTION</td>\n",
- " <td>pana</td>\n",
- " <td>n.</td>\n",
+ " <td>stronÄ™</td>\n",
+ " <td>na</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>7</th>\n",
+ " <th>70</th>\n",
" <td>SUBSTITUTION</td>\n",
- " <td>ja</td>\n",
- " <td>e.</td>\n",
+ " <td>Gocławia</td>\n",
+ " <td>most</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>8</th>\n",
+ " <th>71</th>\n",
" <td>SUBSTITUTION</td>\n",
- " <td>chciałam</td>\n",
- " <td>pracy</td>\n",
+ " <td>gdzie</td>\n",
+ " <td>siekierkowski</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>9</th>\n",
+ " <th>72</th>\n",
" <td>SUBSTITUTION</td>\n",
- " <td>siÄ™</td>\n",
- " <td>a</td>\n",
+ " <td>ma</td>\n",
+ " <td>to</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>10</th>\n",
+ " <th>73</th>\n",
" <td>SUBSTITUTION</td>\n",
- " <td>dowiedzieć</td>\n",
- " <td>to</td>\n",
+ " <td>on</td>\n",
+ " <td>trud</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>11</th>\n",
+ " <th>74</th>\n",
" <td>SUBSTITUTION</td>\n",
- " <td>bo</td>\n",
- " <td>długo</td>\n",
+ " <td>przystanek</td>\n",
+ " <td>i</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>12</th>\n",
- " <td>CORRECT</td>\n",
- " <td>nie</td>\n",
- " <td>nie</td>\n",
+ " <th>75</th>\n",
+ " <td>SUBSTITUTION</td>\n",
+ " <td>pierwszy</td>\n",
+ " <td>czytanek</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>13</th>\n",
+ " <th>76</th>\n",
" <td>SUBSTITUTION</td>\n",
- " <td>bardzo</td>\n",
- " <td>było</td>\n",
+ " <td>sto</td>\n",
+ " <td>pieszczoty</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>14</th>\n",
+ " <th>77</th>\n",
" <td>SUBSTITUTION</td>\n",
- " <td>wiem</td>\n",
- " <td>to</td>\n",
+ " <td>czterdzieści</td>\n",
+ " <td>siÄ™</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>15</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>gdzie</td>\n",
- " <td>dziecko</td>\n",
+ " <th>78</th>\n",
+ " <td>CORRECT</td>\n",
+ " <td>trzy</td>\n",
+ " <td>trzy</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>16</th>\n",
+ " <th>79</th>\n",
" <td>SUBSTITUTION</td>\n",
- " <td>znajduje</td>\n",
- " <td>czuje</td>\n",
+ " <td>znaczy</td>\n",
+ " <td>płaczesz</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>17</th>\n",
+ " <th>80</th>\n",
" <td>CORRECT</td>\n",
- " <td>siÄ™</td>\n",
- " <td>siÄ™</td>\n",
+ " <td>tak</td>\n",
+ " <td>tak</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>18</th>\n",
- " <td>DELETION</td>\n",
- " <td>ulica</td>\n",
- " <td></td>\n",
+ " <th>81</th>\n",
+ " <td>CORRECT</td>\n",
+ " <td>naprawdÄ™</td>\n",
+ " <td>naprawdÄ™</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>19</th>\n",
+ " <th>82</th>\n",
" <td>SUBSTITUTION</td>\n",
- " <td>Zwierzyniecka</td>\n",
- " <td>równie</td>\n",
+ " <td>Most</td>\n",
+ " <td>może</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>20</th>\n",
+ " <th>83</th>\n",
" <td>SUBSTITUTION</td>\n",
- " <td>i</td>\n",
- " <td>szybko</td>\n",
+ " <td>Siekierkowski</td>\n",
+ " <td>kierkowski</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>21</th>\n",
+ " <th>84</th>\n",
" <td>CORRECT</td>\n",
- " <td>jak</td>\n",
- " <td>jak</td>\n",
+ " <td>to</td>\n",
+ " <td>to</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>22</th>\n",
+ " <th>85</th>\n",
" <td>DELETION</td>\n",
- " <td>dojechać</td>\n",
+ " <td>siÄ™</td>\n",
" <td></td>\n",
" </tr>\n",
" <tr>\n",
- " <th>23</th>\n",
+ " <th>86</th>\n",
" <td>DELETION</td>\n",
- " <td>z</td>\n",
+ " <td>zaczyna</td>\n",
" <td></td>\n",
" </tr>\n",
" <tr>\n",
- " <th>24</th>\n",
+ " <th>87</th>\n",
" <td>DELETION</td>\n",
- " <td>Bródna</td>\n",
+ " <td>za</td>\n",
" <td></td>\n",
" </tr>\n",
" <tr>\n",
- " <th>25</th>\n",
+ " <th>88</th>\n",
" <td>DELETION</td>\n",
- " <td>na</td>\n",
+ " <td>Siekierki</td>\n",
" <td></td>\n",
" </tr>\n",
" <tr>\n",
- " <th>26</th>\n",
+ " <th>89</th>\n",
" <td>SUBSTITUTION</td>\n",
- " <td>przykład</td>\n",
- " <td>to</td>\n",
+ " <td>Sanktuarium</td>\n",
+ " <td>zacznÄ…</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>27</th>\n",
+ " <th>90</th>\n",
" <td>SUBSTITUTION</td>\n",
- " <td>?</td>\n",
- " <td>cecha</td>\n",
+ " <td>no</td>\n",
+ " <td>siekierki</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>28</th>\n",
+ " <th>91</th>\n",
" <td>SUBSTITUTION</td>\n",
- " <td>na</td>\n",
- " <td>brud</td>\n",
+ " <td>właśnie</td>\n",
+ " <td>sanktuarium</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>29</th>\n",
+ " <th>92</th>\n",
" <td>SUBSTITUTION</td>\n",
- " <td>ZwierzynieckÄ…</td>\n",
- " <td>ta</td>\n",
+ " <td>przed</td>\n",
+ " <td>w</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>30</th>\n",
- " <td>CORRECT</td>\n",
- " <td>na</td>\n",
- " <td>na</td>\n",
+ " <th>93</th>\n",
+ " <td>SUBSTITUTION</td>\n",
+ " <td>tym</td>\n",
+ " <td>lourdes</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>31</th>\n",
- " <td>DELETION</td>\n",
- " <td>ZwierzynieckÄ…</td>\n",
- " <td></td>\n",
+ " <th>94</th>\n",
+ " <td>SUBSTITUTION</td>\n",
+ " <td>przed</td>\n",
+ " <td>siÄ™</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>32</th>\n",
+ " <th>95</th>\n",
+ " <td>CORRECT</td>\n",
+ " <td>tym</td>\n",
+ " <td>tym</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>96</th>\n",
" <td>DELETION</td>\n",
- " <td>a</td>\n",
+ " <td>przystanek</td>\n",
" <td></td>\n",
" </tr>\n",
" <tr>\n",
- " <th>33</th>\n",
+ " <th>97</th>\n",
" <td>DELETION</td>\n",
- " <td>z</td>\n",
+ " <td>o</td>\n",
" <td></td>\n",
" </tr>\n",
" <tr>\n",
- " <th>34</th>\n",
+ " <th>98</th>\n",
" <td>SUBSTITUTION</td>\n",
- " <td>Bródna</td>\n",
- " <td>przykład</td>\n",
+ " <td>której</td>\n",
+ " <td>przejęty</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>35</th>\n",
+ " <th>99</th>\n",
" <td>SUBSTITUTION</td>\n",
- " <td>z</td>\n",
- " <td>siÄ™</td>\n",
+ " <td>jest</td>\n",
+ " <td>przystanku</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>36</th>\n",
+ " <th>100</th>\n",
" <td>SUBSTITUTION</td>\n",
- " <td>którego</td>\n",
- " <td>ostatnio</td>\n",
+ " <td>sto</td>\n",
+ " <td>który</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>37</th>\n",
+ " <th>101</th>\n",
" <td>SUBSTITUTION</td>\n",
- " <td>miejsca</td>\n",
- " <td>inżynierowie</td>\n",
+ " <td>czterdzieści</td>\n",
+ " <td>torresie</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>38</th>\n",
+ " <th>102</th>\n",
" <td>SUBSTITUTION</td>\n",
- " <td>?</td>\n",
- " <td>i</td>\n",
+ " <td>trzy</td>\n",
+ " <td>czne</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>39</th>\n",
+ " <th>103</th>\n",
" <td>SUBSTITUTION</td>\n",
- " <td>z</td>\n",
- " <td>brudno</td>\n",
+ " <td>najbliższy</td>\n",
+ " <td>edition</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>40</th>\n",
+ " <th>104</th>\n",
" <td>SUBSTITUTION</td>\n",
- " <td>Bródna</td>\n",
- " <td>straszliwy</td>\n",
+ " <td>aha</td>\n",
+ " <td>-</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>41</th>\n",
- " <td>SUBSTITUTION</td>\n",
+ " <th>105</th>\n",
+ " <td>CORRECT</td>\n",
+ " <td>czyli</td>\n",
+ " <td>czyli</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>106</th>\n",
+ " <td>CORRECT</td>\n",
+ " <td>to</td>\n",
" <td>to</td>\n",
- " <td>szok</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>42</th>\n",
+ " <th>107</th>\n",
" <td>SUBSTITUTION</td>\n",
- " <td>jest</td>\n",
- " <td>brodatego</td>\n",
+ " <td>wtedy</td>\n",
+ " <td>wspólny</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>43</th>\n",
+ " <th>108</th>\n",
" <td>CORRECT</td>\n",
- " <td>ulica</td>\n",
- " <td>ulica</td>\n",
+ " <td>przystanek</td>\n",
+ " <td>przystanek</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>44</th>\n",
- " <td>DELETION</td>\n",
- " <td>Wyszogrodzka</td>\n",
- " <td></td>\n",
+ " <th>109</th>\n",
+ " <td>SUBSTITUTION</td>\n",
+ " <td>Małe</td>\n",
+ " <td>małe</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>45</th>\n",
+ " <th>110</th>\n",
" <td>SUBSTITUTION</td>\n",
- " <td>tu</td>\n",
- " <td>wyszogrodzka</td>\n",
+ " <td>Siekierki</td>\n",
+ " <td>siekierki</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>46</th>\n",
+ " <th>111</th>\n",
" <td>CORRECT</td>\n",
- " <td>przy</td>\n",
- " <td>przy</td>\n",
+ " <td>ale</td>\n",
+ " <td>ale</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>47</th>\n",
+ " <th>112</th>\n",
+ " <td>CORRECT</td>\n",
+ " <td>to</td>\n",
+ " <td>to</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>113</th>\n",
+ " <td>CORRECT</td>\n",
+ " <td>nie</td>\n",
+ " <td>nie</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>114</th>\n",
" <td>DELETION</td>\n",
- " <td>Rembielińskiej</td>\n",
+ " <td>jest</td>\n",
" <td></td>\n",
" </tr>\n",
" <tr>\n",
- " <th>48</th>\n",
+ " <th>115</th>\n",
" <td>DELETION</td>\n",
- " <td>czyli</td>\n",
+ " <td>tak</td>\n",
" <td></td>\n",
" </tr>\n",
" <tr>\n",
- " <th>49</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>przy</td>\n",
- " <td>rembielińskiej</td>\n",
+ " <th>116</th>\n",
+ " <td>DELETION</td>\n",
+ " <td>tak</td>\n",
+ " <td></td>\n",
" </tr>\n",
" <tr>\n",
- " <th>50</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>tramwajach</td>\n",
- " <td>ich</td>\n",
+ " <th>117</th>\n",
+ " <td>DELETION</td>\n",
+ " <td>tak</td>\n",
+ " <td></td>\n",
" </tr>\n",
" <tr>\n",
- " <th>51</th>\n",
- " <td>SUBSTITUTION</td>\n",
+ " <th>118</th>\n",
+ " <td>DELETION</td>\n",
" <td>tak</td>\n",
- " <td>cztero</td>\n",
+ " <td></td>\n",
" </tr>\n",
" <tr>\n",
- " <th>52</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>?</td>\n",
- " <td>oto</td>\n",
+ " <th>119</th>\n",
+ " <td>DELETION</td>\n",
+ " <td>na</td>\n",
+ " <td></td>\n",
" </tr>\n",
" <tr>\n",
- " <th>53</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>przy</td>\n",
- " <td>ta</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>54</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>tramwajach</td>\n",
- " <td>jak</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>55</th>\n",
- " <td>CORRECT</td>\n",
- " <td>tak</td>\n",
- " <td>tak</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>56</th>\n",
- " <td>DELETION</td>\n",
- " <td>może</td>\n",
- " <td></td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>57</th>\n",
+ " <th>120</th>\n",
" <td>DELETION</td>\n",
- " <td>pani</td>\n",
+ " <td>wysokości</td>\n",
" <td></td>\n",
" </tr>\n",
" <tr>\n",
- " <th>58</th>\n",
+ " <th>121</th>\n",
" <td>DELETION</td>\n",
- " <td>poczeka</td>\n",
+ " <td>Panoramy</td>\n",
" <td></td>\n",
" </tr>\n",
" <tr>\n",
- " <th>59</th>\n",
+ " <th>122</th>\n",
" <td>SUBSTITUTION</td>\n",
- " <td>sprawdzÄ™</td>\n",
- " <td>dużo</td>\n",
+ " <td>aha</td>\n",
+ " <td>do</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>60</th>\n",
+ " <th>123</th>\n",
" <td>SUBSTITUTION</td>\n",
" <td>dobrze</td>\n",
- " <td>punktów</td>\n",
+ " <td>końca</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>61</th>\n",
+ " <th>124</th>\n",
" <td>SUBSTITUTION</td>\n",
- " <td>dobrze</td>\n",
- " <td><unk></td>\n",
+ " <td>najbliższy</td>\n",
+ " <td>dotrzymać</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>62</th>\n",
+ " <th>125</th>\n",
" <td>SUBSTITUTION</td>\n",
- " <td>pani</td>\n",
- " <td>oni</td>\n",
+ " <td>już</td>\n",
+ " <td>dziÅ›</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>63</th>\n",
+ " <th>126</th>\n",
" <td>SUBSTITUTION</td>\n",
- " <td>sobie</td>\n",
- " <td>żeby</td>\n",
+ " <td>chwileczkÄ™</td>\n",
+ " <td>sÄ…</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>64</th>\n",
+ " <th>127</th>\n",
" <td>SUBSTITUTION</td>\n",
- " <td>podjedzie</td>\n",
- " <td>podróży</td>\n",
+ " <td>czternasta</td>\n",
+ " <td>czternastej</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>65</th>\n",
+ " <th>128</th>\n",
" <td>CORRECT</td>\n",
- " <td>tramwajem</td>\n",
- " <td>tramwajem</td>\n",
+ " <td>czterdzieści</td>\n",
+ " <td>czterdzieści</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>66</th>\n",
+ " <th>129</th>\n",
" <td>CORRECT</td>\n",
- " <td>do</td>\n",
- " <td>do</td>\n",
+ " <td>sześć</td>\n",
+ " <td>sześć</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>67</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>Ronda</td>\n",
- " <td>rondo</td>\n",
+ " <th>130</th>\n",
+ " <td>DELETION</td>\n",
+ " <td>piętnasta</td>\n",
+ " <td></td>\n",
" </tr>\n",
" <tr>\n",
- " <th>68</th>\n",
- " <td>CORRECT</td>\n",
- " <td>Żaba</td>\n",
- " <td>Żaba</td>\n",
+ " <th>131</th>\n",
+ " <td>DELETION</td>\n",
+ " <td>zero</td>\n",
+ " <td></td>\n",
" </tr>\n",
" <tr>\n",
- " <th>69</th>\n",
+ " <th>132</th>\n",
" <td>DELETION</td>\n",
- " <td>tak</td>\n",
+ " <td>jeden</td>\n",
" <td></td>\n",
" </tr>\n",
" <tr>\n",
- " <th>70</th>\n",
+ " <th>133</th>\n",
" <td>DELETION</td>\n",
- " <td>od</td>\n",
+ " <td>aha</td>\n",
" <td></td>\n",
" </tr>\n",
" <tr>\n",
- " <th>71</th>\n",
+ " <th>134</th>\n",
" <td>SUBSTITUTION</td>\n",
- " <td>Ronda</td>\n",
- " <td><unk></td>\n",
+ " <td>no</td>\n",
+ " <td>piętnasto</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>72</th>\n",
+ " <th>135</th>\n",
" <td>SUBSTITUTION</td>\n",
- " <td>Żaba</td>\n",
- " <td>toronto</td>\n",
+ " <td>dobrze</td>\n",
+ " <td>żeruje</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>73</th>\n",
- " <td>CORRECT</td>\n",
- " <td>już</td>\n",
- " <td>już</td>\n",
+ " <th>136</th>\n",
+ " <td>SUBSTITUTION</td>\n",
+ " <td>dziękuję</td>\n",
+ " <td>a</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>74</th>\n",
- " <td>CORRECT</td>\n",
- " <td>sto</td>\n",
- " <td>sto</td>\n",
+ " <th>137</th>\n",
+ " <td>SUBSTITUTION</td>\n",
+ " <td>do</td>\n",
+ " <td>nowy</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>75</th>\n",
- " <td>CORRECT</td>\n",
- " <td>sześćdziesiąt</td>\n",
- " <td>sześćdziesiąt</td>\n",
+ " <th>138</th>\n",
+ " <td>SUBSTITUTION</td>\n",
+ " <td>widzenia</td>\n",
+ " <td>gen.</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>76</th>\n",
- " <td>DELETION</td>\n",
- " <td>dwa</td>\n",
+ " <th>139</th>\n",
+ " <td>SUBSTITUTION</td>\n",
+ " <td>do</td>\n",
" <td></td>\n",
" </tr>\n",
" <tr>\n",
- " <th>77</th>\n",
+ " <th>140</th>\n",
" <td>SUBSTITUTION</td>\n",
- " <td>jest</td>\n",
- " <td>wojsk</td>\n",
+ " <td>widzenia</td>\n",
+ " <td></td>\n",
" </tr>\n",
- " <tr>\n",
- " <th>78</th>\n",
- " <td>CORRECT</td>\n",
- " <td>sto</td>\n",
- " <td>sto</td>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ " step_type reference_word_text hypothesis_word_text\n",
+ "0 DELETION xxx \n",
+ "1 DELETION dzień \n",
+ "2 DELETION dobry \n",
+ "3 SUBSTITUTION dzień dobre\n",
+ "4 SUBSTITUTION dobry dyrektor\n",
+ "5 CORRECT proszÄ™ proszÄ™\n",
+ "6 DELETION pana \n",
+ "7 DELETION ja \n",
+ "8 SUBSTITUTION mam wybaczyć\n",
+ "9 SUBSTITUTION o tryb\n",
+ "10 SUBSTITUTION której numer\n",
+ "11 SUBSTITUTION będzie jeden\n",
+ "12 SUBSTITUTION sto to\n",
+ "13 SUBSTITUTION czterdzieści teresie\n",
+ "14 SUBSTITUTION trzy trzeba\n",
+ "15 CORRECT będzie będzie\n",
+ "16 CORRECT najbliższy najbliższy\n",
+ "17 SUBSTITUTION z ale\n",
+ "18 SUBSTITUTION Alei i\n",
+ "19 SUBSTITUTION Alei tu\n",
+ "20 SUBSTITUTION Witosa aleje\n",
+ "21 SUBSTITUTION w pić\n",
+ "22 SUBSTITUTION stronÄ™ od\n",
+ "23 SUBSTITUTION Gocławia roztropnego\n",
+ "24 SUBSTITUTION z działania\n",
+ "25 SUBSTITUTION tego swego\n",
+ "26 SUBSTITUTION przystanku przystankom\n",
+ "27 CORRECT vis-a-vis vis-a-vis\n",
+ "28 SUBSTITUTION ZUSu zus-u\n",
+ "29 SUBSTITUTION tak to\n",
+ "30 SUBSTITUTION ? jak\n",
+ "31 SUBSTITUTION no mnie\n",
+ "32 CORRECT nie nie\n",
+ "33 SUBSTITUTION nie <unk>\n",
+ "34 SUBSTITUTION tam widać\n",
+ "35 SUBSTITUTION vis-a-vis <unk>\n",
+ "36 SUBSTITUTION Panoramy panoramÄ™\n",
+ "37 CORRECT przez przez\n",
+ "38 SUBSTITUTION Siekierkowski siekierko\n",
+ "39 SUBSTITUTION tam trwałego\n",
+ "40 SUBSTITUTION w tonÄ™\n",
+ "41 SUBSTITUTION stronÄ™ antoniego\n",
+ "42 SUBSTITUTION Gocławia przystanki\n",
+ "43 SUBSTITUTION ale kolejowe\n",
+ "44 CORRECT to to\n",
+ "45 DELETION nie \n",
+ "46 DELETION z \n",
+ "47 DELETION tego \n",
+ "48 DELETION przystanku \n",
+ "49 DELETION Aleja \n",
+ "50 DELETION Witosa \n",
+ "51 DELETION ? \n",
+ "52 DELETION no \n",
+ "53 SUBSTITUTION to było\n",
+ "54 SUBSTITUTION jest coÅ›\n",
+ "55 CORRECT czy czy\n",
+ "56 SUBSTITUTION Bartoszka bartoszka\n",
+ "57 CORRECT na na\n",
+ "58 CORRECT żądanie żądanie\n",
+ "59 SUBSTITUTION wie <unk>\n",
+ "60 SUBSTITUTION pan <unk>\n",
+ "61 SUBSTITUTION gdzie <unk>\n",
+ "62 SUBSTITUTION jest wielbłądy\n",
+ "63 CORRECT siÄ™ siÄ™\n",
+ "64 DELETION zaczyna \n",
+ "65 DELETION Most \n",
+ "66 DELETION Siekierkowski \n",
+ "67 DELETION tam \n",
+ "68 SUBSTITUTION w toczy\n",
+ "69 SUBSTITUTION stronÄ™ na\n",
+ "70 SUBSTITUTION Gocławia most\n",
+ "71 SUBSTITUTION gdzie siekierkowski\n",
+ "72 SUBSTITUTION ma to\n",
+ "73 SUBSTITUTION on trud\n",
+ "74 SUBSTITUTION przystanek i\n",
+ "75 SUBSTITUTION pierwszy czytanek\n",
+ "76 SUBSTITUTION sto pieszczoty\n",
+ "77 SUBSTITUTION czterdzieści się\n",
+ "78 CORRECT trzy trzy\n",
+ "79 SUBSTITUTION znaczy płaczesz\n",
+ "80 CORRECT tak tak\n",
+ "81 CORRECT naprawdÄ™ naprawdÄ™\n",
+ "82 SUBSTITUTION Most może\n",
+ "83 SUBSTITUTION Siekierkowski kierkowski\n",
+ "84 CORRECT to to\n",
+ "85 DELETION siÄ™ \n",
+ "86 DELETION zaczyna \n",
+ "87 DELETION za \n",
+ "88 DELETION Siekierki \n",
+ "89 SUBSTITUTION Sanktuarium zacznÄ…\n",
+ "90 SUBSTITUTION no siekierki\n",
+ "91 SUBSTITUTION właśnie sanktuarium\n",
+ "92 SUBSTITUTION przed w\n",
+ "93 SUBSTITUTION tym lourdes\n",
+ "94 SUBSTITUTION przed siÄ™\n",
+ "95 CORRECT tym tym\n",
+ "96 DELETION przystanek \n",
+ "97 DELETION o \n",
+ "98 SUBSTITUTION której przejęty\n",
+ "99 SUBSTITUTION jest przystanku\n",
+ "100 SUBSTITUTION sto który\n",
+ "101 SUBSTITUTION czterdzieści torresie\n",
+ "102 SUBSTITUTION trzy czne\n",
+ "103 SUBSTITUTION najbliższy edition\n",
+ "104 SUBSTITUTION aha -\n",
+ "105 CORRECT czyli czyli\n",
+ "106 CORRECT to to\n",
+ "107 SUBSTITUTION wtedy wspólny\n",
+ "108 CORRECT przystanek przystanek\n",
+ "109 SUBSTITUTION Małe małe\n",
+ "110 SUBSTITUTION Siekierki siekierki\n",
+ "111 CORRECT ale ale\n",
+ "112 CORRECT to to\n",
+ "113 CORRECT nie nie\n",
+ "114 DELETION jest \n",
+ "115 DELETION tak \n",
+ "116 DELETION tak \n",
+ "117 DELETION tak \n",
+ "118 DELETION tak \n",
+ "119 DELETION na \n",
+ "120 DELETION wysokości \n",
+ "121 DELETION Panoramy \n",
+ "122 SUBSTITUTION aha do\n",
+ "123 SUBSTITUTION dobrze końca\n",
+ "124 SUBSTITUTION najbliższy dotrzymać\n",
+ "125 SUBSTITUTION już dziś\n",
+ "126 SUBSTITUTION chwileczkÄ™ sÄ…\n",
+ "127 SUBSTITUTION czternasta czternastej\n",
+ "128 CORRECT czterdzieści czterdzieści\n",
+ "129 CORRECT sześć sześć\n",
+ "130 DELETION piętnasta \n",
+ "131 DELETION zero \n",
+ "132 DELETION jeden \n",
+ "133 DELETION aha \n",
+ "134 SUBSTITUTION no piętnasto\n",
+ "135 SUBSTITUTION dobrze żeruje\n",
+ "136 SUBSTITUTION dziękuję a\n",
+ "137 SUBSTITUTION do nowy\n",
+ "138 SUBSTITUTION widzenia gen.\n",
+ "139 SUBSTITUTION do \n",
+ "140 SUBSTITUTION widzenia "
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "\n"
+ ]
+ },
+ {
+ "data": {
+ "text/html": [
+ "<div>\n",
+ "<style scoped>\n",
+ " .dataframe tbody tr th:only-of-type {\n",
+ " vertical-align: middle;\n",
+ " }\n",
+ "\n",
+ " .dataframe tbody tr th {\n",
+ " vertical-align: top;\n",
+ " }\n",
+ "\n",
+ " .dataframe thead th {\n",
+ " text-align: right;\n",
+ " }\n",
+ "</style>\n",
+ "<table border=\"1\" class=\"dataframe\">\n",
+ " <thead>\n",
+ " <tr style=\"text-align: right;\">\n",
+ " <th></th>\n",
+ " <th>step_type</th>\n",
+ " <th>reference_word_pos</th>\n",
+ " <th>reference_word_text</th>\n",
+ " <th>hypothesis_word_pos</th>\n",
+ " <th>hypothesis_word_text</th>\n",
" </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
" <tr>\n",
- " <th>79</th>\n",
- " <td>CORRECT</td>\n",
- " <td>sześćdziesiąt</td>\n",
- " <td>sześćdziesiąt</td>\n",
+ " <th>0</th>\n",
+ " <td>DELETION</td>\n",
+ " <td>PRON</td>\n",
+ " <td>xxx</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
" </tr>\n",
" <tr>\n",
- " <th>80</th>\n",
+ " <th>1</th>\n",
" <td>DELETION</td>\n",
- " <td>dwa</td>\n",
+ " <td>NOUN</td>\n",
+ " <td>dzień</td>\n",
+ " <td></td>\n",
" <td></td>\n",
" </tr>\n",
" <tr>\n",
- " <th>81</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>tak</td>\n",
- " <td>ta</td>\n",
+ " <th>2</th>\n",
+ " <td>CORRECT</td>\n",
+ " <td>ADJ</td>\n",
+ " <td>dobry</td>\n",
+ " <td>ADJ</td>\n",
+ " <td>dobre</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>82</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>i</td>\n",
- " <td><unk></td>\n",
+ " <th>3</th>\n",
+ " <td>CORRECT</td>\n",
+ " <td>NOUN</td>\n",
+ " <td>dzień</td>\n",
+ " <td>NOUN</td>\n",
+ " <td>dyrektor</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>83</th>\n",
+ " <th>4</th>\n",
" <td>SUBSTITUTION</td>\n",
- " <td>sto</td>\n",
- " <td>trzysta</td>\n",
+ " <td>ADJ</td>\n",
+ " <td>dobry</td>\n",
+ " <td>VERB</td>\n",
+ " <td>proszÄ™</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>84</th>\n",
+ " <th>5</th>\n",
" <td>CORRECT</td>\n",
- " <td>sześćdziesiąt</td>\n",
- " <td>sześćdziesiąt</td>\n",
+ " <td>VERB</td>\n",
+ " <td>proszÄ™</td>\n",
+ " <td>VERB</td>\n",
+ " <td>wybaczyć</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>85</th>\n",
- " <td>DELETION</td>\n",
- " <td>dwa</td>\n",
- " <td></td>\n",
+ " <th>6</th>\n",
+ " <td>CORRECT</td>\n",
+ " <td>NOUN</td>\n",
+ " <td>pana</td>\n",
+ " <td>NOUN</td>\n",
+ " <td>tryb</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>86</th>\n",
- " <td>DELETION</td>\n",
- " <td>tam</td>\n",
- " <td></td>\n",
+ " <th>7</th>\n",
+ " <td>SUBSTITUTION</td>\n",
+ " <td>PRON</td>\n",
+ " <td>ja</td>\n",
+ " <td>NOUN</td>\n",
+ " <td>numer</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>87</th>\n",
+ " <th>8</th>\n",
" <td>SUBSTITUTION</td>\n",
- " <td>dojadÄ™</td>\n",
- " <td>rataja</td>\n",
+ " <td>VERB</td>\n",
+ " <td>mam</td>\n",
+ " <td>ADJ</td>\n",
+ " <td>jeden</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>88</th>\n",
+ " <th>9</th>\n",
" <td>SUBSTITUTION</td>\n",
- " <td>do</td>\n",
- " <td><unk></td>\n",
+ " <td>ADP</td>\n",
+ " <td>o</td>\n",
+ " <td>SCONJ</td>\n",
+ " <td>to</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>89</th>\n",
- " <td>CORRECT</td>\n",
- " <td>tej</td>\n",
- " <td>tej</td>\n",
+ " <th>10</th>\n",
+ " <td>SUBSTITUTION</td>\n",
+ " <td>DET</td>\n",
+ " <td>której</td>\n",
+ " <td>NOUN</td>\n",
+ " <td>teresie</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>90</th>\n",
- " <td>DELETION</td>\n",
- " <td>ulicy</td>\n",
- " <td></td>\n",
+ " <th>11</th>\n",
+ " <td>CORRECT</td>\n",
+ " <td>VERB</td>\n",
+ " <td>będzie</td>\n",
+ " <td>VERB</td>\n",
+ " <td>trzeba</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>91</th>\n",
+ " <th>12</th>\n",
" <td>SUBSTITUTION</td>\n",
- " <td>tak</td>\n",
- " <td><unk></td>\n",
+ " <td>NUM</td>\n",
+ " <td>sto</td>\n",
+ " <td>AUX</td>\n",
+ " <td>będzie</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>92</th>\n",
+ " <th>13</th>\n",
" <td>CORRECT</td>\n",
- " <td>może</td>\n",
- " <td>może</td>\n",
+ " <td>ADJ</td>\n",
+ " <td>czterdzieści</td>\n",
+ " <td>ADJ</td>\n",
+ " <td>najbliższy</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>93</th>\n",
+ " <th>14</th>\n",
" <td>DELETION</td>\n",
- " <td>pani</td>\n",
+ " <td>NUM</td>\n",
+ " <td>trzy</td>\n",
" <td></td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>94</th>\n",
- " <td>DELETION</td>\n",
- " <td>wysiąść</td>\n",
" <td></td>\n",
" </tr>\n",
" <tr>\n",
- " <th>95</th>\n",
+ " <th>15</th>\n",
" <td>DELETION</td>\n",
- " <td>na</td>\n",
+ " <td>AUX</td>\n",
+ " <td>będzie</td>\n",
" <td></td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>96</th>\n",
- " <td>DELETION</td>\n",
- " <td>przystanku</td>\n",
" <td></td>\n",
" </tr>\n",
" <tr>\n",
- " <th>97</th>\n",
- " <td>DELETION</td>\n",
- " <td>Bartycka</td>\n",
- " <td></td>\n",
+ " <th>16</th>\n",
+ " <td>SUBSTITUTION</td>\n",
+ " <td>ADJ</td>\n",
+ " <td>najbliższy</td>\n",
+ " <td>CCONJ</td>\n",
+ " <td>ale</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>98</th>\n",
+ " <th>17</th>\n",
" <td>SUBSTITUTION</td>\n",
- " <td>albo</td>\n",
- " <td>pojawić</td>\n",
+ " <td>ADP</td>\n",
+ " <td>z</td>\n",
+ " <td>PART</td>\n",
+ " <td>i</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>99</th>\n",
+ " <th>18</th>\n",
" <td>SUBSTITUTION</td>\n",
- " <td>Sielce</td>\n",
- " <td>siÄ™</td>\n",
+ " <td>NOUN</td>\n",
+ " <td>Alei</td>\n",
+ " <td>ADV</td>\n",
+ " <td>tu</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>100</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>Bartycka</td>\n",
- " <td>trzy</td>\n",
+ " <th>19</th>\n",
+ " <td>CORRECT</td>\n",
+ " <td>NOUN</td>\n",
+ " <td>Alei</td>\n",
+ " <td>NOUN</td>\n",
+ " <td>aleje</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>101</th>\n",
+ " <th>20</th>\n",
" <td>SUBSTITUTION</td>\n",
- " <td>albo</td>\n",
- " <td>stÄ…d</td>\n",
+ " <td>PROPN</td>\n",
+ " <td>Witosa</td>\n",
+ " <td>VERB</td>\n",
+ " <td>pić</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>102</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>?</td>\n",
- " <td><unk></td>\n",
+ " <th>21</th>\n",
+ " <td>CORRECT</td>\n",
+ " <td>ADP</td>\n",
+ " <td>w</td>\n",
+ " <td>ADP</td>\n",
+ " <td>od</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>103</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>Sielce</td>\n",
- " <td><unk></td>\n",
+ " <th>22</th>\n",
+ " <td>DELETION</td>\n",
+ " <td>NOUN</td>\n",
+ " <td>stronÄ™</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
" </tr>\n",
" <tr>\n",
- " <th>104</th>\n",
+ " <th>23</th>\n",
" <td>SUBSTITUTION</td>\n",
- " <td>Sielce</td>\n",
- " <td><unk></td>\n",
+ " <td>PROPN</td>\n",
+ " <td>Gocławia</td>\n",
+ " <td>ADJ</td>\n",
+ " <td>roztropnego</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>105</th>\n",
+ " <th>24</th>\n",
" <td>SUBSTITUTION</td>\n",
- " <td>tak</td>\n",
- " <td><unk></td>\n",
+ " <td>ADP</td>\n",
+ " <td>z</td>\n",
+ " <td>NOUN</td>\n",
+ " <td>działania</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>106</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>?</td>\n",
- " <td><unk></td>\n",
+ " <th>25</th>\n",
+ " <td>CORRECT</td>\n",
+ " <td>DET</td>\n",
+ " <td>tego</td>\n",
+ " <td>DET</td>\n",
+ " <td>swego</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>107</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>tak</td>\n",
- " <td>berty</td>\n",
+ " <th>26</th>\n",
+ " <td>CORRECT</td>\n",
+ " <td>NOUN</td>\n",
+ " <td>przystanku</td>\n",
+ " <td>NOUN</td>\n",
+ " <td>przystankom</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>108</th>\n",
+ " <th>27</th>\n",
" <td>SUBSTITUTION</td>\n",
- " <td>aha</td>\n",
- " <td>coraz</td>\n",
+ " <td>NOUN</td>\n",
+ " <td>vis</td>\n",
+ " <td>VERB</td>\n",
+ " <td>vis</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>109</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>i</td>\n",
- " <td>szybciej</td>\n",
+ " <th>28</th>\n",
+ " <td>CORRECT</td>\n",
+ " <td>PROPN</td>\n",
+ " <td>-</td>\n",
+ " <td>PROPN</td>\n",
+ " <td>-</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>110</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>tam</td>\n",
- " <td>bartycka</td>\n",
+ " <th>29</th>\n",
+ " <td>CORRECT</td>\n",
+ " <td>PROPN</td>\n",
+ " <td>a</td>\n",
+ " <td>PROPN</td>\n",
+ " <td>a</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>111</th>\n",
+ " <th>30</th>\n",
+ " <td>CORRECT</td>\n",
+ " <td>PUNCT</td>\n",
+ " <td>-</td>\n",
+ " <td>PUNCT</td>\n",
+ " <td>-</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>31</th>\n",
+ " <td>INSERTION</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>X</td>\n",
+ " <td>vis</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>32</th>\n",
" <td>SUBSTITUTION</td>\n",
- " <td>w</td>\n",
- " <td><unk></td>\n",
+ " <td>ADP</td>\n",
+ " <td>vis</td>\n",
+ " <td>PROPN</td>\n",
+ " <td>zus</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>112</th>\n",
+ " <th>33</th>\n",
+ " <td>CORRECT</td>\n",
+ " <td>PROPN</td>\n",
+ " <td>ZUSu</td>\n",
+ " <td>PROPN</td>\n",
+ " <td>-</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>34</th>\n",
" <td>SUBSTITUTION</td>\n",
- " <td>pobliżu</td>\n",
- " <td>trzema</td>\n",
+ " <td>ADV</td>\n",
+ " <td>tak</td>\n",
+ " <td>ADP</td>\n",
+ " <td>u</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>113</th>\n",
+ " <th>35</th>\n",
" <td>SUBSTITUTION</td>\n",
- " <td>jest</td>\n",
- " <td>trzeba</td>\n",
+ " <td>PUNCT</td>\n",
+ " <td>?</td>\n",
+ " <td>PRON</td>\n",
+ " <td>to</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>114</th>\n",
+ " <th>36</th>\n",
" <td>SUBSTITUTION</td>\n",
- " <td>ta</td>\n",
- " <td>siÄ™</td>\n",
+ " <td>PART</td>\n",
+ " <td>no</td>\n",
+ " <td>SCONJ</td>\n",
+ " <td>jak</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>115</th>\n",
+ " <th>37</th>\n",
" <td>SUBSTITUTION</td>\n",
- " <td>ulica</td>\n",
- " <td>trochÄ™</td>\n",
+ " <td>PART</td>\n",
+ " <td>nie</td>\n",
+ " <td>PRON</td>\n",
+ " <td>mnie</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>116</th>\n",
+ " <th>38</th>\n",
" <td>CORRECT</td>\n",
- " <td>tak</td>\n",
- " <td>tak</td>\n",
+ " <td>PART</td>\n",
+ " <td>nie</td>\n",
+ " <td>PART</td>\n",
+ " <td>nie</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>117</th>\n",
- " <td>DELETION</td>\n",
- " <td>?</td>\n",
- " <td></td>\n",
+ " <th>39</th>\n",
+ " <td>SUBSTITUTION</td>\n",
+ " <td>ADV</td>\n",
+ " <td>tam</td>\n",
+ " <td>PUNCT</td>\n",
+ " <td><</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>118</th>\n",
- " <td>DELETION</td>\n",
- " <td>a</td>\n",
- " <td></td>\n",
+ " <th>40</th>\n",
+ " <td>CORRECT</td>\n",
+ " <td>NOUN</td>\n",
+ " <td>vis</td>\n",
+ " <td>NOUN</td>\n",
+ " <td>unk</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>119</th>\n",
+ " <th>41</th>\n",
" <td>DELETION</td>\n",
- " <td>Zwierzyniecka</td>\n",
+ " <td>PROPN</td>\n",
+ " <td>-</td>\n",
" <td></td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>120</th>\n",
- " <td>DELETION</td>\n",
- " <td>wysoki</td>\n",
" <td></td>\n",
" </tr>\n",
" <tr>\n",
- " <th>121</th>\n",
+ " <th>42</th>\n",
" <td>DELETION</td>\n",
- " <td>numer</td>\n",
+ " <td>PROPN</td>\n",
+ " <td>a</td>\n",
+ " <td></td>\n",
" <td></td>\n",
" </tr>\n",
" <tr>\n",
- " <th>122</th>\n",
- " <td>DELETION</td>\n",
- " <td>ma</td>\n",
- " <td></td>\n",
+ " <th>43</th>\n",
+ " <td>CORRECT</td>\n",
+ " <td>PUNCT</td>\n",
+ " <td>-</td>\n",
+ " <td>PUNCT</td>\n",
+ " <td>></td>\n",
" </tr>\n",
" <tr>\n",
- " <th>123</th>\n",
- " <td>DELETION</td>\n",
- " <td>pani</td>\n",
- " <td></td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>124</th>\n",
- " <td>DELETION</td>\n",
- " <td>?</td>\n",
- " <td></td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>125</th>\n",
- " <td>DELETION</td>\n",
- " <td>Zwierzyniecka</td>\n",
- " <td></td>\n",
+ " <th>44</th>\n",
+ " <td>CORRECT</td>\n",
+ " <td>VERB</td>\n",
+ " <td>vis</td>\n",
+ " <td>VERB</td>\n",
+ " <td>widać</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>126</th>\n",
- " <td>DELETION</td>\n",
- " <td>zaraz</td>\n",
- " <td></td>\n",
+ " <th>45</th>\n",
+ " <td>SUBSTITUTION</td>\n",
+ " <td>VERB</td>\n",
+ " <td>Panoramy</td>\n",
+ " <td>PUNCT</td>\n",
+ " <td><</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>127</th>\n",
- " <td>DELETION</td>\n",
- " <td>momencik</td>\n",
- " <td></td>\n",
+ " <th>46</th>\n",
+ " <td>SUBSTITUTION</td>\n",
+ " <td>ADP</td>\n",
+ " <td>przez</td>\n",
+ " <td>NOUN</td>\n",
+ " <td>unk</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>128</th>\n",
+ " <th>47</th>\n",
" <td>SUBSTITUTION</td>\n",
- " <td>osiem</td>\n",
- " <td>jak</td>\n",
+ " <td>PROPN</td>\n",
+ " <td>Siekierkowski</td>\n",
+ " <td>PUNCT</td>\n",
+ " <td>></td>\n",
" </tr>\n",
" <tr>\n",
- " <th>129</th>\n",
+ " <th>48</th>\n",
" <td>SUBSTITUTION</td>\n",
- " <td>A</td>\n",
- " <td>i</td>\n",
+ " <td>ADV</td>\n",
+ " <td>tam</td>\n",
+ " <td>NOUN</td>\n",
+ " <td>panoramÄ™</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>130</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>Zwierzyniecka</td>\n",
- " <td>te</td>\n",
+ " <th>49</th>\n",
+ " <td>CORRECT</td>\n",
+ " <td>ADP</td>\n",
+ " <td>w</td>\n",
+ " <td>ADP</td>\n",
+ " <td>przez</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>131</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>to</td>\n",
- " <td>plany</td>\n",
+ " <th>50</th>\n",
+ " <td>CORRECT</td>\n",
+ " <td>NOUN</td>\n",
+ " <td>stronÄ™</td>\n",
+ " <td>NOUN</td>\n",
+ " <td>siekierko</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>132</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>to</td>\n",
- " <td>stały</td>\n",
+ " <th>51</th>\n",
+ " <td>DELETION</td>\n",
+ " <td>PROPN</td>\n",
+ " <td>Gocławia</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
" </tr>\n",
" <tr>\n",
- " <th>133</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>przy</td>\n",
- " <td>siÄ™</td>\n",
+ " <th>52</th>\n",
+ " <td>DELETION</td>\n",
+ " <td>CCONJ</td>\n",
+ " <td>ale</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
" </tr>\n",
" <tr>\n",
- " <th>134</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>Sielce</td>\n",
- " <td>słynne</td>\n",
+ " <th>53</th>\n",
+ " <td>DELETION</td>\n",
+ " <td>PRON</td>\n",
+ " <td>to</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
" </tr>\n",
" <tr>\n",
- " <th>135</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>trza</td>\n",
- " <td>ciężko</td>\n",
+ " <th>54</th>\n",
+ " <td>DELETION</td>\n",
+ " <td>PART</td>\n",
+ " <td>nie</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
" </tr>\n",
" <tr>\n",
- " <th>136</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>wysiąść</td>\n",
- " <td>dyszÄ…c</td>\n",
+ " <th>55</th>\n",
+ " <td>DELETION</td>\n",
+ " <td>ADP</td>\n",
+ " <td>z</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
" </tr>\n",
" <tr>\n",
- " <th>137</th>\n",
+ " <th>56</th>\n",
" <td>SUBSTITUTION</td>\n",
- " <td>przy</td>\n",
- " <td>i</td>\n",
+ " <td>DET</td>\n",
+ " <td>tego</td>\n",
+ " <td>ADJ</td>\n",
+ " <td>trwałego</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>138</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>Sielce</td>\n",
- " <td>numer</td>\n",
+ " <th>57</th>\n",
+ " <td>CORRECT</td>\n",
+ " <td>NOUN</td>\n",
+ " <td>przystanku</td>\n",
+ " <td>NOUN</td>\n",
+ " <td>tonÄ™</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>139</th>\n",
+ " <th>58</th>\n",
" <td>SUBSTITUTION</td>\n",
- " <td>tak</td>\n",
- " <td>ewidencyjny</td>\n",
+ " <td>NOUN</td>\n",
+ " <td>Aleja</td>\n",
+ " <td>ADJ</td>\n",
+ " <td>antoniego</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>140</th>\n",
+ " <th>59</th>\n",
" <td>SUBSTITUTION</td>\n",
- " <td>?</td>\n",
- " <td><unk></td>\n",
+ " <td>PROPN</td>\n",
+ " <td>Witosa</td>\n",
+ " <td>NOUN</td>\n",
+ " <td>przystanki</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>141</th>\n",
+ " <th>60</th>\n",
" <td>SUBSTITUTION</td>\n",
- " <td>tak</td>\n",
- " <td>nowy</td>\n",
+ " <td>PUNCT</td>\n",
+ " <td>?</td>\n",
+ " <td>ADJ</td>\n",
+ " <td>kolejowe</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>142</th>\n",
+ " <th>61</th>\n",
" <td>SUBSTITUTION</td>\n",
- " <td>przystanek</td>\n",
- " <td>typ</td>\n",
+ " <td>PART</td>\n",
+ " <td>no</td>\n",
+ " <td>AUX</td>\n",
+ " <td>to</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>143</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>Sielce</td>\n",
- " <td><unk></td>\n",
+ " <th>62</th>\n",
+ " <td>CORRECT</td>\n",
+ " <td>AUX</td>\n",
+ " <td>to</td>\n",
+ " <td>AUX</td>\n",
+ " <td>było</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>144</th>\n",
+ " <th>63</th>\n",
" <td>SUBSTITUTION</td>\n",
- " <td>aha</td>\n",
- " <td>-</td>\n",
+ " <td>VERB</td>\n",
+ " <td>jest</td>\n",
+ " <td>PRON</td>\n",
+ " <td>coÅ›</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>145</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>tak</td>\n",
- " <td>siÄ™</td>\n",
+ " <th>64</th>\n",
+ " <td>CORRECT</td>\n",
+ " <td>CCONJ</td>\n",
+ " <td>czy</td>\n",
+ " <td>CCONJ</td>\n",
+ " <td>czy</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>146</th>\n",
+ " <th>65</th>\n",
" <td>SUBSTITUTION</td>\n",
- " <td>no</td>\n",
- " <td>-</td>\n",
+ " <td>PROPN</td>\n",
+ " <td>Bartoszka</td>\n",
+ " <td>NOUN</td>\n",
+ " <td>bartoszka</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>147</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>dobrze</td>\n",
- " <td>dla</td>\n",
+ " <th>66</th>\n",
+ " <td>CORRECT</td>\n",
+ " <td>ADP</td>\n",
+ " <td>na</td>\n",
+ " <td>ADP</td>\n",
+ " <td>na</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>148</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>a</td>\n",
- " <td>mnie</td>\n",
+ " <th>67</th>\n",
+ " <td>CORRECT</td>\n",
+ " <td>NOUN</td>\n",
+ " <td>żądanie</td>\n",
+ " <td>NOUN</td>\n",
+ " <td>żądanie</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>149</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>Sielce</td>\n",
- " <td>trwało</td>\n",
+ " <th>68</th>\n",
+ " <td>INSERTION</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>PUNCT</td>\n",
+ " <td><</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>150</th>\n",
- " <td>CORRECT</td>\n",
- " <td>to</td>\n",
- " <td>to</td>\n",
+ " <th>69</th>\n",
+ " <td>INSERTION</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>X</td>\n",
+ " <td>unk</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>151</th>\n",
- " <td>DELETION</td>\n",
- " <td>znaczy</td>\n",
+ " <th>70</th>\n",
+ " <td>INSERTION</td>\n",
+ " <td></td>\n",
" <td></td>\n",
+ " <td>PUNCT</td>\n",
+ " <td>></td>\n",
" </tr>\n",
" <tr>\n",
- " <th>152</th>\n",
+ " <th>71</th>\n",
" <td>SUBSTITUTION</td>\n",
- " <td>jaka</td>\n",
- " <td>trzy</td>\n",
+ " <td>VERB</td>\n",
+ " <td>wie</td>\n",
+ " <td>PUNCT</td>\n",
+ " <td><</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>153</th>\n",
+ " <th>72</th>\n",
" <td>SUBSTITUTION</td>\n",
- " <td>to</td>\n",
- " <td>trzody</td>\n",
+ " <td>NOUN</td>\n",
+ " <td>pan</td>\n",
+ " <td>PROPN</td>\n",
+ " <td>unk</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>154</th>\n",
+ " <th>73</th>\n",
" <td>SUBSTITUTION</td>\n",
- " <td>już</td>\n",
- " <td>ścięte</td>\n",
+ " <td>ADV</td>\n",
+ " <td>gdzie</td>\n",
+ " <td>PUNCT</td>\n",
+ " <td>></td>\n",
" </tr>\n",
" <tr>\n",
- " <th>155</th>\n",
+ " <th>74</th>\n",
" <td>SUBSTITUTION</td>\n",
+ " <td>AUX</td>\n",
" <td>jest</td>\n",
- " <td>tato</td>\n",
+ " <td>PUNCT</td>\n",
+ " <td><</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>156</th>\n",
+ " <th>75</th>\n",
" <td>SUBSTITUTION</td>\n",
- " <td>dzielnica</td>\n",
- " <td>taneczne</td>\n",
+ " <td>PRON</td>\n",
+ " <td>siÄ™</td>\n",
+ " <td>NOUN</td>\n",
+ " <td>unk</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>157</th>\n",
+ " <th>76</th>\n",
" <td>SUBSTITUTION</td>\n",
- " <td>to</td>\n",
- " <td><unk></td>\n",
+ " <td>VERB</td>\n",
+ " <td>zaczyna</td>\n",
+ " <td>PUNCT</td>\n",
+ " <td>></td>\n",
" </tr>\n",
" <tr>\n",
- " <th>158</th>\n",
+ " <th>77</th>\n",
" <td>CORRECT</td>\n",
- " <td>ta</td>\n",
- " <td>ta</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>159</th>\n",
- " <td>DELETION</td>\n",
- " <td>jest</td>\n",
- " <td></td>\n",
+ " <td>NOUN</td>\n",
+ " <td>Most</td>\n",
+ " <td>NOUN</td>\n",
+ " <td>wielbłądy</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>160</th>\n",
+ " <th>78</th>\n",
" <td>SUBSTITUTION</td>\n",
- " <td>przy</td>\n",
- " <td>notatka</td>\n",
+ " <td>PROPN</td>\n",
+ " <td>Siekierkowski</td>\n",
+ " <td>PRON</td>\n",
+ " <td>siÄ™</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>161</th>\n",
+ " <th>79</th>\n",
" <td>SUBSTITUTION</td>\n",
- " <td>ulica</td>\n",
- " <td>siÄ™</td>\n",
+ " <td>ADV</td>\n",
+ " <td>tam</td>\n",
+ " <td>VERB</td>\n",
+ " <td>toczy</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>162</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>Gagarina</td>\n",
- " <td>tutaj</td>\n",
+ " <th>80</th>\n",
+ " <td>CORRECT</td>\n",
+ " <td>ADP</td>\n",
+ " <td>w</td>\n",
+ " <td>ADP</td>\n",
+ " <td>na</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>163</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>a</td>\n",
- " <td>także</td>\n",
+ " <th>81</th>\n",
+ " <td>CORRECT</td>\n",
+ " <td>NOUN</td>\n",
+ " <td>stronÄ™</td>\n",
+ " <td>NOUN</td>\n",
+ " <td>most</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>164</th>\n",
+ " <th>82</th>\n",
" <td>SUBSTITUTION</td>\n",
- " <td>przy</td>\n",
- " <td>kilka</td>\n",
+ " <td>PROPN</td>\n",
+ " <td>Gocławia</td>\n",
+ " <td>ADJ</td>\n",
+ " <td>siekierkowski</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>165</th>\n",
+ " <th>83</th>\n",
" <td>SUBSTITUTION</td>\n",
- " <td>ulicy</td>\n",
- " <td>tutaj</td>\n",
+ " <td>ADV</td>\n",
+ " <td>gdzie</td>\n",
+ " <td>AUX</td>\n",
+ " <td>to</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>166</th>\n",
+ " <th>84</th>\n",
" <td>SUBSTITUTION</td>\n",
- " <td>Gagarina</td>\n",
- " <td>trzy</td>\n",
+ " <td>VERB</td>\n",
+ " <td>ma</td>\n",
+ " <td>NOUN</td>\n",
+ " <td>trud</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>167</th>\n",
+ " <th>85</th>\n",
" <td>SUBSTITUTION</td>\n",
- " <td>czyli</td>\n",
- " <td>czy</td>\n",
+ " <td>PRON</td>\n",
+ " <td>on</td>\n",
+ " <td>CCONJ</td>\n",
+ " <td>i</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>168</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>to</td>\n",
- " <td>cztery</td>\n",
+ " <th>86</th>\n",
+ " <td>CORRECT</td>\n",
+ " <td>NOUN</td>\n",
+ " <td>przystanek</td>\n",
+ " <td>NOUN</td>\n",
+ " <td>czytanek</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>169</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>jest</td>\n",
- " <td>dni</td>\n",
+ " <th>87</th>\n",
+ " <td>DELETION</td>\n",
+ " <td>ADJ</td>\n",
+ " <td>pierwszy</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
" </tr>\n",
" <tr>\n",
- " <th>170</th>\n",
+ " <th>88</th>\n",
" <td>SUBSTITUTION</td>\n",
- " <td>tam</td>\n",
- " <td><unk></td>\n",
+ " <td>NUM</td>\n",
+ " <td>sto</td>\n",
+ " <td>NOUN</td>\n",
+ " <td>pieszczoty</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>171</th>\n",
+ " <th>89</th>\n",
" <td>SUBSTITUTION</td>\n",
- " <td>Mokotów</td>\n",
- " <td>płyty</td>\n",
+ " <td>PROPN</td>\n",
+ " <td>czterdzieści</td>\n",
+ " <td>PRON</td>\n",
+ " <td>siÄ™</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>172</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>po</td>\n",
- " <td>darin</td>\n",
+ " <th>90</th>\n",
+ " <td>CORRECT</td>\n",
+ " <td>NUM</td>\n",
+ " <td>trzy</td>\n",
+ " <td>NUM</td>\n",
+ " <td>trzy</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>173</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>prostu</td>\n",
- " <td>nakryta</td>\n",
+ " <th>91</th>\n",
+ " <td>CORRECT</td>\n",
+ " <td>VERB</td>\n",
+ " <td>znaczy</td>\n",
+ " <td>VERB</td>\n",
+ " <td>płaczesz</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>174</th>\n",
- " <td>SUBSTITUTION</td>\n",
+ " <th>92</th>\n",
+ " <td>CORRECT</td>\n",
+ " <td>PART</td>\n",
+ " <td>tak</td>\n",
+ " <td>PART</td>\n",
" <td>tak</td>\n",
- " <td>plakatów</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>175</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>?</td>\n",
- " <td>pod</td>\n",
+ " <th>93</th>\n",
+ " <td>CORRECT</td>\n",
+ " <td>PART</td>\n",
+ " <td>naprawdÄ™</td>\n",
+ " <td>PART</td>\n",
+ " <td>naprawdÄ™</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>176</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>tak</td>\n",
- " <td>hutach</td>\n",
+ " <th>94</th>\n",
+ " <td>DELETION</td>\n",
+ " <td>NOUN</td>\n",
+ " <td>Most</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
" </tr>\n",
" <tr>\n",
- " <th>177</th>\n",
+ " <th>95</th>\n",
" <td>SUBSTITUTION</td>\n",
- " <td>Siekierki</td>\n",
- " <td>siekierkowskÄ…</td>\n",
+ " <td>ADJ</td>\n",
+ " <td>Siekierkowski</td>\n",
+ " <td>PART</td>\n",
+ " <td>może</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>178</th>\n",
+ " <th>96</th>\n",
" <td>SUBSTITUTION</td>\n",
- " <td>Mokotów</td>\n",
- " <td><unk></td>\n",
+ " <td>AUX</td>\n",
+ " <td>to</td>\n",
+ " <td>PROPN</td>\n",
+ " <td>kierkowski</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>179</th>\n",
+ " <th>97</th>\n",
" <td>CORRECT</td>\n",
- " <td>a</td>\n",
- " <td>a</td>\n",
+ " <td>PRON</td>\n",
+ " <td>siÄ™</td>\n",
+ " <td>PRON</td>\n",
+ " <td>to</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>180</th>\n",
- " <td>DELETION</td>\n",
- " <td>Siekierki</td>\n",
- " <td></td>\n",
+ " <th>98</th>\n",
+ " <td>CORRECT</td>\n",
+ " <td>VERB</td>\n",
+ " <td>zaczyna</td>\n",
+ " <td>VERB</td>\n",
+ " <td>zacznÄ…</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>181</th>\n",
+ " <th>99</th>\n",
" <td>DELETION</td>\n",
- " <td>Mokotów</td>\n",
+ " <td>ADP</td>\n",
+ " <td>za</td>\n",
" <td></td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>182</th>\n",
- " <td>DELETION</td>\n",
- " <td>i</td>\n",
" <td></td>\n",
" </tr>\n",
" <tr>\n",
- " <th>183</th>\n",
+ " <th>100</th>\n",
" <td>DELETION</td>\n",
- " <td>tam</td>\n",
+ " <td>PROPN</td>\n",
+ " <td>Siekierki</td>\n",
" <td></td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>184</th>\n",
- " <td>DELETION</td>\n",
- " <td>jak</td>\n",
" <td></td>\n",
" </tr>\n",
" <tr>\n",
- " <th>185</th>\n",
- " <td>DELETION</td>\n",
- " <td>pani</td>\n",
- " <td></td>\n",
+ " <th>101</th>\n",
+ " <td>CORRECT</td>\n",
+ " <td>NOUN</td>\n",
+ " <td>Sanktuarium</td>\n",
+ " <td>NOUN</td>\n",
+ " <td>siekierki</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>186</th>\n",
+ " <th>102</th>\n",
" <td>DELETION</td>\n",
- " <td>wysiÄ…dzie</td>\n",
+ " <td>PART</td>\n",
+ " <td>no</td>\n",
+ " <td></td>\n",
" <td></td>\n",
" </tr>\n",
" <tr>\n",
- " <th>187</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>to</td>\n",
- " <td>siekierki</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>188</th>\n",
+ " <th>103</th>\n",
" <td>SUBSTITUTION</td>\n",
- " <td>trza</td>\n",
- " <td>hoszowski</td>\n",
+ " <td>ADV</td>\n",
+ " <td>właśnie</td>\n",
+ " <td>NOUN</td>\n",
+ " <td>sanktuarium</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>189</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>wejść</td>\n",
- " <td>czytelnik</td>\n",
+ " <th>104</th>\n",
+ " <td>CORRECT</td>\n",
+ " <td>ADP</td>\n",
+ " <td>przed</td>\n",
+ " <td>ADP</td>\n",
+ " <td>w</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>190</th>\n",
+ " <th>105</th>\n",
" <td>SUBSTITUTION</td>\n",
- " <td>w</td>\n",
- " <td>wyszedł</td>\n",
+ " <td>PRON</td>\n",
+ " <td>tym</td>\n",
+ " <td>NOUN</td>\n",
+ " <td>lourdes</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>191</th>\n",
+ " <th>106</th>\n",
" <td>SUBSTITUTION</td>\n",
- " <td>lewo</td>\n",
- " <td>od</td>\n",
+ " <td>ADP</td>\n",
+ " <td>przed</td>\n",
+ " <td>PRON</td>\n",
+ " <td>siÄ™</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>192</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>w</td>\n",
- " <td>swoich</td>\n",
+ " <th>107</th>\n",
+ " <td>CORRECT</td>\n",
+ " <td>PRON</td>\n",
+ " <td>tym</td>\n",
+ " <td>PRON</td>\n",
+ " <td>tym</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>193</th>\n",
+ " <th>108</th>\n",
" <td>SUBSTITUTION</td>\n",
- " <td>ulicÄ™</td>\n",
- " <td>kolegów</td>\n",
+ " <td>NOUN</td>\n",
+ " <td>przystanek</td>\n",
+ " <td>ADJ</td>\n",
+ " <td>przejęty</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>194</th>\n",
+ " <th>109</th>\n",
" <td>SUBSTITUTION</td>\n",
- " <td>Nehru</td>\n",
- " <td>uliczek</td>\n",
+ " <td>ADP</td>\n",
+ " <td>o</td>\n",
+ " <td>NOUN</td>\n",
+ " <td>przystanku</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>195</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>i</td>\n",
- " <td><unk></td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>196</th>\n",
+ " <th>110</th>\n",
" <td>CORRECT</td>\n",
- " <td>od</td>\n",
- " <td>od</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>197</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>Nehru</td>\n",
- " <td><unk></td>\n",
+ " <td>DET</td>\n",
+ " <td>której</td>\n",
+ " <td>DET</td>\n",
+ " <td>który</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>198</th>\n",
+ " <th>111</th>\n",
" <td>CORRECT</td>\n",
- " <td>odchodzi</td>\n",
- " <td>odchodzi</td>\n",
+ " <td>VERB</td>\n",
+ " <td>jest</td>\n",
+ " <td>VERB</td>\n",
+ " <td>torresie</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>199</th>\n",
+ " <th>112</th>\n",
" <td>DELETION</td>\n",
- " <td>Zwierzyniecka</td>\n",
+ " <td>NUM</td>\n",
+ " <td>sto</td>\n",
+ " <td></td>\n",
" <td></td>\n",
" </tr>\n",
" <tr>\n",
- " <th>200</th>\n",
+ " <th>113</th>\n",
" <td>DELETION</td>\n",
- " <td>w</td>\n",
+ " <td>NUM</td>\n",
+ " <td>czterdzieści</td>\n",
+ " <td></td>\n",
" <td></td>\n",
" </tr>\n",
" <tr>\n",
- " <th>201</th>\n",
+ " <th>114</th>\n",
" <td>SUBSTITUTION</td>\n",
- " <td>lewo</td>\n",
- " <td>służy</td>\n",
+ " <td>NUM</td>\n",
+ " <td>trzy</td>\n",
+ " <td>ADJ</td>\n",
+ " <td>czne</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>202</th>\n",
+ " <th>115</th>\n",
" <td>SUBSTITUTION</td>\n",
- " <td>w</td>\n",
- " <td>nie</td>\n",
+ " <td>ADJ</td>\n",
+ " <td>najbliższy</td>\n",
+ " <td>PROPN</td>\n",
+ " <td>edition</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>203</th>\n",
+ " <th>116</th>\n",
" <td>SUBSTITUTION</td>\n",
- " <td>lewo</td>\n",
- " <td>tylko</td>\n",
+ " <td>NOUN</td>\n",
+ " <td>aha</td>\n",
+ " <td>PUNCT</td>\n",
+ " <td>-</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>204</th>\n",
+ " <th>117</th>\n",
+ " <td>CORRECT</td>\n",
+ " <td>CCONJ</td>\n",
+ " <td>czyli</td>\n",
+ " <td>CCONJ</td>\n",
+ " <td>czyli</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>118</th>\n",
" <td>SUBSTITUTION</td>\n",
- " <td>i</td>\n",
- " <td><unk></td>\n",
+ " <td>PART</td>\n",
+ " <td>to</td>\n",
+ " <td>AUX</td>\n",
+ " <td>to</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>205</th>\n",
+ " <th>119</th>\n",
" <td>SUBSTITUTION</td>\n",
- " <td>ulica</td>\n",
- " <td>na</td>\n",
+ " <td>ADV</td>\n",
+ " <td>wtedy</td>\n",
+ " <td>ADJ</td>\n",
+ " <td>wspólny</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>206</th>\n",
+ " <th>120</th>\n",
+ " <td>CORRECT</td>\n",
+ " <td>NOUN</td>\n",
+ " <td>przystanek</td>\n",
+ " <td>NOUN</td>\n",
+ " <td>przystanek</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>121</th>\n",
+ " <td>CORRECT</td>\n",
+ " <td>ADJ</td>\n",
+ " <td>Małe</td>\n",
+ " <td>ADJ</td>\n",
+ " <td>małe</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>122</th>\n",
" <td>SUBSTITUTION</td>\n",
- " <td>Nehru</td>\n",
- " <td>ulicach</td>\n",
+ " <td>PROPN</td>\n",
+ " <td>Siekierki</td>\n",
+ " <td>NOUN</td>\n",
+ " <td>siekierki</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>207</th>\n",
+ " <th>123</th>\n",
+ " <td>CORRECT</td>\n",
+ " <td>CCONJ</td>\n",
+ " <td>ale</td>\n",
+ " <td>CCONJ</td>\n",
+ " <td>ale</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>124</th>\n",
" <td>SUBSTITUTION</td>\n",
- " <td>?</td>\n",
- " <td><unk></td>\n",
+ " <td>AUX</td>\n",
+ " <td>to</td>\n",
+ " <td>PRON</td>\n",
+ " <td>to</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>208</th>\n",
+ " <th>125</th>\n",
" <td>CORRECT</td>\n",
+ " <td>PART</td>\n",
+ " <td>nie</td>\n",
+ " <td>PART</td>\n",
+ " <td>nie</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>126</th>\n",
+ " <td>DELETION</td>\n",
+ " <td>VERB</td>\n",
+ " <td>jest</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>127</th>\n",
+ " <td>DELETION</td>\n",
+ " <td>ADV</td>\n",
+ " <td>tak</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>128</th>\n",
+ " <td>DELETION</td>\n",
+ " <td>ADV</td>\n",
" <td>tak</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>129</th>\n",
+ " <td>DELETION</td>\n",
+ " <td>ADV</td>\n",
" <td>tak</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
" </tr>\n",
" <tr>\n",
- " <th>209</th>\n",
+ " <th>130</th>\n",
" <td>DELETION</td>\n",
- " <td>Nehru</td>\n",
+ " <td>ADV</td>\n",
+ " <td>tak</td>\n",
+ " <td></td>\n",
" <td></td>\n",
" </tr>\n",
" <tr>\n",
- " <th>210</th>\n",
+ " <th>131</th>\n",
+ " <td>CORRECT</td>\n",
+ " <td>ADP</td>\n",
+ " <td>na</td>\n",
+ " <td>ADP</td>\n",
+ " <td>do</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>132</th>\n",
" <td>DELETION</td>\n",
- " <td>dobrze</td>\n",
+ " <td>NOUN</td>\n",
+ " <td>wysokości</td>\n",
+ " <td></td>\n",
" <td></td>\n",
" </tr>\n",
" <tr>\n",
- " <th>211</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>dziękuję</td>\n",
- " <td>numeru</td>\n",
+ " <th>133</th>\n",
+ " <td>CORRECT</td>\n",
+ " <td>NOUN</td>\n",
+ " <td>Panoramy</td>\n",
+ " <td>NOUN</td>\n",
+ " <td>końca</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>212</th>\n",
+ " <th>134</th>\n",
" <td>SUBSTITUTION</td>\n",
- " <td>panu</td>\n",
- " <td>krytykuje</td>\n",
+ " <td>NOUN</td>\n",
+ " <td>aha</td>\n",
+ " <td>VERB</td>\n",
+ " <td>dotrzymać</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>213</th>\n",
+ " <th>135</th>\n",
+ " <td>CORRECT</td>\n",
+ " <td>ADV</td>\n",
+ " <td>dobrze</td>\n",
+ " <td>ADV</td>\n",
+ " <td>dziÅ›</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>136</th>\n",
+ " <td>DELETION</td>\n",
+ " <td>ADJ</td>\n",
+ " <td>najbliższy</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>137</th>\n",
+ " <td>DELETION</td>\n",
+ " <td>PART</td>\n",
+ " <td>już</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>138</th>\n",
" <td>SUBSTITUTION</td>\n",
- " <td>bardzo</td>\n",
- " <td>pan</td>\n",
+ " <td>NOUN</td>\n",
+ " <td>chwileczkÄ™</td>\n",
+ " <td>AUX</td>\n",
+ " <td>sÄ…</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>214</th>\n",
+ " <th>139</th>\n",
+ " <td>CORRECT</td>\n",
+ " <td>ADJ</td>\n",
+ " <td>czternasta</td>\n",
+ " <td>ADJ</td>\n",
+ " <td>czternastej</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>140</th>\n",
+ " <td>CORRECT</td>\n",
+ " <td>NUM</td>\n",
+ " <td>czterdzieści</td>\n",
+ " <td>NUM</td>\n",
+ " <td>czterdzieści</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>141</th>\n",
+ " <td>CORRECT</td>\n",
+ " <td>NUM</td>\n",
+ " <td>sześć</td>\n",
+ " <td>NUM</td>\n",
+ " <td>sześć</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>142</th>\n",
+ " <td>INSERTION</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>NOUN</td>\n",
+ " <td>piętnasto</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>143</th>\n",
" <td>SUBSTITUTION</td>\n",
- " <td>proszÄ™</td>\n",
- " <td><unk></td>\n",
+ " <td>ADJ</td>\n",
+ " <td>piętnasta</td>\n",
+ " <td>VERB</td>\n",
+ " <td>żeruje</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>215</th>\n",
+ " <th>144</th>\n",
" <td>SUBSTITUTION</td>\n",
+ " <td>PART</td>\n",
+ " <td>zero</td>\n",
+ " <td>CCONJ</td>\n",
+ " <td>a</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>145</th>\n",
+ " <td>CORRECT</td>\n",
+ " <td>ADJ</td>\n",
+ " <td>jeden</td>\n",
+ " <td>ADJ</td>\n",
+ " <td>nowy</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>146</th>\n",
+ " <td>CORRECT</td>\n",
+ " <td>X</td>\n",
+ " <td>aha</td>\n",
+ " <td>X</td>\n",
+ " <td>gen</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>147</th>\n",
+ " <td>DELETION</td>\n",
+ " <td>PART</td>\n",
+ " <td>no</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>148</th>\n",
+ " <td>DELETION</td>\n",
+ " <td>ADV</td>\n",
+ " <td>dobrze</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>149</th>\n",
+ " <td>DELETION</td>\n",
+ " <td>VERB</td>\n",
+ " <td>dziękuję</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>150</th>\n",
+ " <td>DELETION</td>\n",
+ " <td>ADP</td>\n",
" <td>do</td>\n",
- " <td>badania</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
" </tr>\n",
" <tr>\n",
- " <th>216</th>\n",
- " <td>SUBSTITUTION</td>\n",
+ " <th>151</th>\n",
+ " <td>DELETION</td>\n",
+ " <td>NOUN</td>\n",
" <td>widzenia</td>\n",
- " <td><unk></td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
" </tr>\n",
" <tr>\n",
- " <th>217</th>\n",
+ " <th>152</th>\n",
" <td>SUBSTITUTION</td>\n",
+ " <td>ADP</td>\n",
" <td>do</td>\n",
- " <td></td>\n",
+ " <td>PUNCT</td>\n",
+ " <td>.</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>218</th>\n",
+ " <th>153</th>\n",
" <td>SUBSTITUTION</td>\n",
+ " <td>NOUN</td>\n",
" <td>widzenia</td>\n",
+ " <td>SPACE</td>\n",
" <td></td>\n",
" </tr>\n",
" </tbody>\n",
@@ -7158,226 +7535,317 @@
"</div>"
],
"text/plain": [
- " step_type reference_word_text hypothesis_word_text\n",
- "0 DELETION xxx \n",
- "1 DELETION dzień \n",
- "2 DELETION dobry \n",
- "3 DELETION dzień \n",
- "4 DELETION dobry \n",
- "5 SUBSTITUTION proszÄ™ niedobre\n",
- "6 SUBSTITUTION pana n.\n",
- "7 SUBSTITUTION ja e.\n",
- "8 SUBSTITUTION chciałam pracy\n",
- "9 SUBSTITUTION siÄ™ a\n",
- "10 SUBSTITUTION dowiedzieć to\n",
- "11 SUBSTITUTION bo długo\n",
- "12 CORRECT nie nie\n",
- "13 SUBSTITUTION bardzo było\n",
- "14 SUBSTITUTION wiem to\n",
- "15 SUBSTITUTION gdzie dziecko\n",
- "16 SUBSTITUTION znajduje czuje\n",
- "17 CORRECT siÄ™ siÄ™\n",
- "18 DELETION ulica \n",
- "19 SUBSTITUTION Zwierzyniecka równie\n",
- "20 SUBSTITUTION i szybko\n",
- "21 CORRECT jak jak\n",
- "22 DELETION dojechać \n",
- "23 DELETION z \n",
- "24 DELETION Bródna \n",
- "25 DELETION na \n",
- "26 SUBSTITUTION przykład to\n",
- "27 SUBSTITUTION ? cecha\n",
- "28 SUBSTITUTION na brud\n",
- "29 SUBSTITUTION ZwierzynieckÄ… ta\n",
- "30 CORRECT na na\n",
- "31 DELETION ZwierzynieckÄ… \n",
- "32 DELETION a \n",
- "33 DELETION z \n",
- "34 SUBSTITUTION Bródna przykład\n",
- "35 SUBSTITUTION z siÄ™\n",
- "36 SUBSTITUTION którego ostatnio\n",
- "37 SUBSTITUTION miejsca inżynierowie\n",
- "38 SUBSTITUTION ? i\n",
- "39 SUBSTITUTION z brudno\n",
- "40 SUBSTITUTION Bródna straszliwy\n",
- "41 SUBSTITUTION to szok\n",
- "42 SUBSTITUTION jest brodatego\n",
- "43 CORRECT ulica ulica\n",
- "44 DELETION Wyszogrodzka \n",
- "45 SUBSTITUTION tu wyszogrodzka\n",
- "46 CORRECT przy przy\n",
- "47 DELETION Rembielińskiej \n",
- "48 DELETION czyli \n",
- "49 SUBSTITUTION przy rembielińskiej\n",
- "50 SUBSTITUTION tramwajach ich\n",
- "51 SUBSTITUTION tak cztero\n",
- "52 SUBSTITUTION ? oto\n",
- "53 SUBSTITUTION przy ta\n",
- "54 SUBSTITUTION tramwajach jak\n",
- "55 CORRECT tak tak\n",
- "56 DELETION może \n",
- "57 DELETION pani \n",
- "58 DELETION poczeka \n",
- "59 SUBSTITUTION sprawdzę dużo\n",
- "60 SUBSTITUTION dobrze punktów\n",
- "61 SUBSTITUTION dobrze <unk>\n",
- "62 SUBSTITUTION pani oni\n",
- "63 SUBSTITUTION sobie żeby\n",
- "64 SUBSTITUTION podjedzie podróży\n",
- "65 CORRECT tramwajem tramwajem\n",
- "66 CORRECT do do\n",
- "67 SUBSTITUTION Ronda rondo\n",
- "68 CORRECT Żaba Żaba\n",
- "69 DELETION tak \n",
- "70 DELETION od \n",
- "71 SUBSTITUTION Ronda <unk>\n",
- "72 SUBSTITUTION Żaba toronto\n",
- "73 CORRECT już już\n",
- "74 CORRECT sto sto\n",
- "75 CORRECT sześćdziesiąt sześćdziesiąt\n",
- "76 DELETION dwa \n",
- "77 SUBSTITUTION jest wojsk\n",
- "78 CORRECT sto sto\n",
- "79 CORRECT sześćdziesiąt sześćdziesiąt\n",
- "80 DELETION dwa \n",
- "81 SUBSTITUTION tak ta\n",
- "82 SUBSTITUTION i <unk>\n",
- "83 SUBSTITUTION sto trzysta\n",
- "84 CORRECT sześćdziesiąt sześćdziesiąt\n",
- "85 DELETION dwa \n",
- "86 DELETION tam \n",
- "87 SUBSTITUTION dojadÄ™ rataja\n",
- "88 SUBSTITUTION do <unk>\n",
- "89 CORRECT tej tej\n",
- "90 DELETION ulicy \n",
- "91 SUBSTITUTION tak <unk>\n",
- "92 CORRECT może może\n",
- "93 DELETION pani \n",
- "94 DELETION wysiąść \n",
- "95 DELETION na \n",
- "96 DELETION przystanku \n",
- "97 DELETION Bartycka \n",
- "98 SUBSTITUTION albo pojawić\n",
- "99 SUBSTITUTION Sielce siÄ™\n",
- "100 SUBSTITUTION Bartycka trzy\n",
- "101 SUBSTITUTION albo stÄ…d\n",
- "102 SUBSTITUTION ? <unk>\n",
- "103 SUBSTITUTION Sielce <unk>\n",
- "104 SUBSTITUTION Sielce <unk>\n",
- "105 SUBSTITUTION tak <unk>\n",
- "106 SUBSTITUTION ? <unk>\n",
- "107 SUBSTITUTION tak berty\n",
- "108 SUBSTITUTION aha coraz\n",
- "109 SUBSTITUTION i szybciej\n",
- "110 SUBSTITUTION tam bartycka\n",
- "111 SUBSTITUTION w <unk>\n",
- "112 SUBSTITUTION pobliżu trzema\n",
- "113 SUBSTITUTION jest trzeba\n",
- "114 SUBSTITUTION ta siÄ™\n",
- "115 SUBSTITUTION ulica trochÄ™\n",
- "116 CORRECT tak tak\n",
- "117 DELETION ? \n",
- "118 DELETION a \n",
- "119 DELETION Zwierzyniecka \n",
- "120 DELETION wysoki \n",
- "121 DELETION numer \n",
- "122 DELETION ma \n",
- "123 DELETION pani \n",
- "124 DELETION ? \n",
- "125 DELETION Zwierzyniecka \n",
- "126 DELETION zaraz \n",
- "127 DELETION momencik \n",
- "128 SUBSTITUTION osiem jak\n",
- "129 SUBSTITUTION A i\n",
- "130 SUBSTITUTION Zwierzyniecka te\n",
- "131 SUBSTITUTION to plany\n",
- "132 SUBSTITUTION to stały\n",
- "133 SUBSTITUTION przy siÄ™\n",
- "134 SUBSTITUTION Sielce słynne\n",
- "135 SUBSTITUTION trza ciężko\n",
- "136 SUBSTITUTION wysiąść dysząc\n",
- "137 SUBSTITUTION przy i\n",
- "138 SUBSTITUTION Sielce numer\n",
- "139 SUBSTITUTION tak ewidencyjny\n",
- "140 SUBSTITUTION ? <unk>\n",
- "141 SUBSTITUTION tak nowy\n",
- "142 SUBSTITUTION przystanek typ\n",
- "143 SUBSTITUTION Sielce <unk>\n",
- "144 SUBSTITUTION aha -\n",
- "145 SUBSTITUTION tak siÄ™\n",
- "146 SUBSTITUTION no -\n",
- "147 SUBSTITUTION dobrze dla\n",
- "148 SUBSTITUTION a mnie\n",
- "149 SUBSTITUTION Sielce trwało\n",
- "150 CORRECT to to\n",
- "151 DELETION znaczy \n",
- "152 SUBSTITUTION jaka trzy\n",
- "153 SUBSTITUTION to trzody\n",
- "154 SUBSTITUTION już ścięte\n",
- "155 SUBSTITUTION jest tato\n",
- "156 SUBSTITUTION dzielnica taneczne\n",
- "157 SUBSTITUTION to <unk>\n",
- "158 CORRECT ta ta\n",
- "159 DELETION jest \n",
- "160 SUBSTITUTION przy notatka\n",
- "161 SUBSTITUTION ulica siÄ™\n",
- "162 SUBSTITUTION Gagarina tutaj\n",
- "163 SUBSTITUTION a także\n",
- "164 SUBSTITUTION przy kilka\n",
- "165 SUBSTITUTION ulicy tutaj\n",
- "166 SUBSTITUTION Gagarina trzy\n",
- "167 SUBSTITUTION czyli czy\n",
- "168 SUBSTITUTION to cztery\n",
- "169 SUBSTITUTION jest dni\n",
- "170 SUBSTITUTION tam <unk>\n",
- "171 SUBSTITUTION Mokotów płyty\n",
- "172 SUBSTITUTION po darin\n",
- "173 SUBSTITUTION prostu nakryta\n",
- "174 SUBSTITUTION tak plakatów\n",
- "175 SUBSTITUTION ? pod\n",
- "176 SUBSTITUTION tak hutach\n",
- "177 SUBSTITUTION Siekierki siekierkowskÄ…\n",
- "178 SUBSTITUTION Mokotów <unk>\n",
- "179 CORRECT a a\n",
- "180 DELETION Siekierki \n",
- "181 DELETION Mokotów \n",
- "182 DELETION i \n",
- "183 DELETION tam \n",
- "184 DELETION jak \n",
- "185 DELETION pani \n",
- "186 DELETION wysiÄ…dzie \n",
- "187 SUBSTITUTION to siekierki\n",
- "188 SUBSTITUTION trza hoszowski\n",
- "189 SUBSTITUTION wejść czytelnik\n",
- "190 SUBSTITUTION w wyszedł\n",
- "191 SUBSTITUTION lewo od\n",
- "192 SUBSTITUTION w swoich\n",
- "193 SUBSTITUTION ulicę kolegów\n",
- "194 SUBSTITUTION Nehru uliczek\n",
- "195 SUBSTITUTION i <unk>\n",
- "196 CORRECT od od\n",
- "197 SUBSTITUTION Nehru <unk>\n",
- "198 CORRECT odchodzi odchodzi\n",
- "199 DELETION Zwierzyniecka \n",
- "200 DELETION w \n",
- "201 SUBSTITUTION lewo służy\n",
- "202 SUBSTITUTION w nie\n",
- "203 SUBSTITUTION lewo tylko\n",
- "204 SUBSTITUTION i <unk>\n",
- "205 SUBSTITUTION ulica na\n",
- "206 SUBSTITUTION Nehru ulicach\n",
- "207 SUBSTITUTION ? <unk>\n",
- "208 CORRECT tak tak\n",
- "209 DELETION Nehru \n",
- "210 DELETION dobrze \n",
- "211 SUBSTITUTION dziękuję numeru\n",
- "212 SUBSTITUTION panu krytykuje\n",
- "213 SUBSTITUTION bardzo pan\n",
- "214 SUBSTITUTION proszÄ™ <unk>\n",
- "215 SUBSTITUTION do badania\n",
- "216 SUBSTITUTION widzenia <unk>\n",
- "217 SUBSTITUTION do \n",
- "218 SUBSTITUTION widzenia "
+ " step_type reference_word_pos reference_word_text hypothesis_word_pos \\\n",
+ "0 DELETION PRON xxx \n",
+ "1 DELETION NOUN dzień \n",
+ "2 CORRECT ADJ dobry ADJ \n",
+ "3 CORRECT NOUN dzień NOUN \n",
+ "4 SUBSTITUTION ADJ dobry VERB \n",
+ "5 CORRECT VERB proszÄ™ VERB \n",
+ "6 CORRECT NOUN pana NOUN \n",
+ "7 SUBSTITUTION PRON ja NOUN \n",
+ "8 SUBSTITUTION VERB mam ADJ \n",
+ "9 SUBSTITUTION ADP o SCONJ \n",
+ "10 SUBSTITUTION DET której NOUN \n",
+ "11 CORRECT VERB będzie VERB \n",
+ "12 SUBSTITUTION NUM sto AUX \n",
+ "13 CORRECT ADJ czterdzieści ADJ \n",
+ "14 DELETION NUM trzy \n",
+ "15 DELETION AUX będzie \n",
+ "16 SUBSTITUTION ADJ najbliższy CCONJ \n",
+ "17 SUBSTITUTION ADP z PART \n",
+ "18 SUBSTITUTION NOUN Alei ADV \n",
+ "19 CORRECT NOUN Alei NOUN \n",
+ "20 SUBSTITUTION PROPN Witosa VERB \n",
+ "21 CORRECT ADP w ADP \n",
+ "22 DELETION NOUN stronÄ™ \n",
+ "23 SUBSTITUTION PROPN Gocławia ADJ \n",
+ "24 SUBSTITUTION ADP z NOUN \n",
+ "25 CORRECT DET tego DET \n",
+ "26 CORRECT NOUN przystanku NOUN \n",
+ "27 SUBSTITUTION NOUN vis VERB \n",
+ "28 CORRECT PROPN - PROPN \n",
+ "29 CORRECT PROPN a PROPN \n",
+ "30 CORRECT PUNCT - PUNCT \n",
+ "31 INSERTION X \n",
+ "32 SUBSTITUTION ADP vis PROPN \n",
+ "33 CORRECT PROPN ZUSu PROPN \n",
+ "34 SUBSTITUTION ADV tak ADP \n",
+ "35 SUBSTITUTION PUNCT ? PRON \n",
+ "36 SUBSTITUTION PART no SCONJ \n",
+ "37 SUBSTITUTION PART nie PRON \n",
+ "38 CORRECT PART nie PART \n",
+ "39 SUBSTITUTION ADV tam PUNCT \n",
+ "40 CORRECT NOUN vis NOUN \n",
+ "41 DELETION PROPN - \n",
+ "42 DELETION PROPN a \n",
+ "43 CORRECT PUNCT - PUNCT \n",
+ "44 CORRECT VERB vis VERB \n",
+ "45 SUBSTITUTION VERB Panoramy PUNCT \n",
+ "46 SUBSTITUTION ADP przez NOUN \n",
+ "47 SUBSTITUTION PROPN Siekierkowski PUNCT \n",
+ "48 SUBSTITUTION ADV tam NOUN \n",
+ "49 CORRECT ADP w ADP \n",
+ "50 CORRECT NOUN stronÄ™ NOUN \n",
+ "51 DELETION PROPN Gocławia \n",
+ "52 DELETION CCONJ ale \n",
+ "53 DELETION PRON to \n",
+ "54 DELETION PART nie \n",
+ "55 DELETION ADP z \n",
+ "56 SUBSTITUTION DET tego ADJ \n",
+ "57 CORRECT NOUN przystanku NOUN \n",
+ "58 SUBSTITUTION NOUN Aleja ADJ \n",
+ "59 SUBSTITUTION PROPN Witosa NOUN \n",
+ "60 SUBSTITUTION PUNCT ? ADJ \n",
+ "61 SUBSTITUTION PART no AUX \n",
+ "62 CORRECT AUX to AUX \n",
+ "63 SUBSTITUTION VERB jest PRON \n",
+ "64 CORRECT CCONJ czy CCONJ \n",
+ "65 SUBSTITUTION PROPN Bartoszka NOUN \n",
+ "66 CORRECT ADP na ADP \n",
+ "67 CORRECT NOUN żądanie NOUN \n",
+ "68 INSERTION PUNCT \n",
+ "69 INSERTION X \n",
+ "70 INSERTION PUNCT \n",
+ "71 SUBSTITUTION VERB wie PUNCT \n",
+ "72 SUBSTITUTION NOUN pan PROPN \n",
+ "73 SUBSTITUTION ADV gdzie PUNCT \n",
+ "74 SUBSTITUTION AUX jest PUNCT \n",
+ "75 SUBSTITUTION PRON siÄ™ NOUN \n",
+ "76 SUBSTITUTION VERB zaczyna PUNCT \n",
+ "77 CORRECT NOUN Most NOUN \n",
+ "78 SUBSTITUTION PROPN Siekierkowski PRON \n",
+ "79 SUBSTITUTION ADV tam VERB \n",
+ "80 CORRECT ADP w ADP \n",
+ "81 CORRECT NOUN stronÄ™ NOUN \n",
+ "82 SUBSTITUTION PROPN Gocławia ADJ \n",
+ "83 SUBSTITUTION ADV gdzie AUX \n",
+ "84 SUBSTITUTION VERB ma NOUN \n",
+ "85 SUBSTITUTION PRON on CCONJ \n",
+ "86 CORRECT NOUN przystanek NOUN \n",
+ "87 DELETION ADJ pierwszy \n",
+ "88 SUBSTITUTION NUM sto NOUN \n",
+ "89 SUBSTITUTION PROPN czterdzieści PRON \n",
+ "90 CORRECT NUM trzy NUM \n",
+ "91 CORRECT VERB znaczy VERB \n",
+ "92 CORRECT PART tak PART \n",
+ "93 CORRECT PART naprawdÄ™ PART \n",
+ "94 DELETION NOUN Most \n",
+ "95 SUBSTITUTION ADJ Siekierkowski PART \n",
+ "96 SUBSTITUTION AUX to PROPN \n",
+ "97 CORRECT PRON siÄ™ PRON \n",
+ "98 CORRECT VERB zaczyna VERB \n",
+ "99 DELETION ADP za \n",
+ "100 DELETION PROPN Siekierki \n",
+ "101 CORRECT NOUN Sanktuarium NOUN \n",
+ "102 DELETION PART no \n",
+ "103 SUBSTITUTION ADV właśnie NOUN \n",
+ "104 CORRECT ADP przed ADP \n",
+ "105 SUBSTITUTION PRON tym NOUN \n",
+ "106 SUBSTITUTION ADP przed PRON \n",
+ "107 CORRECT PRON tym PRON \n",
+ "108 SUBSTITUTION NOUN przystanek ADJ \n",
+ "109 SUBSTITUTION ADP o NOUN \n",
+ "110 CORRECT DET której DET \n",
+ "111 CORRECT VERB jest VERB \n",
+ "112 DELETION NUM sto \n",
+ "113 DELETION NUM czterdzieści \n",
+ "114 SUBSTITUTION NUM trzy ADJ \n",
+ "115 SUBSTITUTION ADJ najbliższy PROPN \n",
+ "116 SUBSTITUTION NOUN aha PUNCT \n",
+ "117 CORRECT CCONJ czyli CCONJ \n",
+ "118 SUBSTITUTION PART to AUX \n",
+ "119 SUBSTITUTION ADV wtedy ADJ \n",
+ "120 CORRECT NOUN przystanek NOUN \n",
+ "121 CORRECT ADJ Małe ADJ \n",
+ "122 SUBSTITUTION PROPN Siekierki NOUN \n",
+ "123 CORRECT CCONJ ale CCONJ \n",
+ "124 SUBSTITUTION AUX to PRON \n",
+ "125 CORRECT PART nie PART \n",
+ "126 DELETION VERB jest \n",
+ "127 DELETION ADV tak \n",
+ "128 DELETION ADV tak \n",
+ "129 DELETION ADV tak \n",
+ "130 DELETION ADV tak \n",
+ "131 CORRECT ADP na ADP \n",
+ "132 DELETION NOUN wysokości \n",
+ "133 CORRECT NOUN Panoramy NOUN \n",
+ "134 SUBSTITUTION NOUN aha VERB \n",
+ "135 CORRECT ADV dobrze ADV \n",
+ "136 DELETION ADJ najbliższy \n",
+ "137 DELETION PART już \n",
+ "138 SUBSTITUTION NOUN chwileczkÄ™ AUX \n",
+ "139 CORRECT ADJ czternasta ADJ \n",
+ "140 CORRECT NUM czterdzieści NUM \n",
+ "141 CORRECT NUM sześć NUM \n",
+ "142 INSERTION NOUN \n",
+ "143 SUBSTITUTION ADJ piętnasta VERB \n",
+ "144 SUBSTITUTION PART zero CCONJ \n",
+ "145 CORRECT ADJ jeden ADJ \n",
+ "146 CORRECT X aha X \n",
+ "147 DELETION PART no \n",
+ "148 DELETION ADV dobrze \n",
+ "149 DELETION VERB dziękuję \n",
+ "150 DELETION ADP do \n",
+ "151 DELETION NOUN widzenia \n",
+ "152 SUBSTITUTION ADP do PUNCT \n",
+ "153 SUBSTITUTION NOUN widzenia SPACE \n",
+ "\n",
+ " hypothesis_word_text \n",
+ "0 \n",
+ "1 \n",
+ "2 dobre \n",
+ "3 dyrektor \n",
+ "4 proszÄ™ \n",
+ "5 wybaczyć \n",
+ "6 tryb \n",
+ "7 numer \n",
+ "8 jeden \n",
+ "9 to \n",
+ "10 teresie \n",
+ "11 trzeba \n",
+ "12 będzie \n",
+ "13 najbliższy \n",
+ "14 \n",
+ "15 \n",
+ "16 ale \n",
+ "17 i \n",
+ "18 tu \n",
+ "19 aleje \n",
+ "20 pić \n",
+ "21 od \n",
+ "22 \n",
+ "23 roztropnego \n",
+ "24 działania \n",
+ "25 swego \n",
+ "26 przystankom \n",
+ "27 vis \n",
+ "28 - \n",
+ "29 a \n",
+ "30 - \n",
+ "31 vis \n",
+ "32 zus \n",
+ "33 - \n",
+ "34 u \n",
+ "35 to \n",
+ "36 jak \n",
+ "37 mnie \n",
+ "38 nie \n",
+ "39 < \n",
+ "40 unk \n",
+ "41 \n",
+ "42 \n",
+ "43 > \n",
+ "44 widać \n",
+ "45 < \n",
+ "46 unk \n",
+ "47 > \n",
+ "48 panoramÄ™ \n",
+ "49 przez \n",
+ "50 siekierko \n",
+ "51 \n",
+ "52 \n",
+ "53 \n",
+ "54 \n",
+ "55 \n",
+ "56 trwałego \n",
+ "57 tonÄ™ \n",
+ "58 antoniego \n",
+ "59 przystanki \n",
+ "60 kolejowe \n",
+ "61 to \n",
+ "62 było \n",
+ "63 coÅ› \n",
+ "64 czy \n",
+ "65 bartoszka \n",
+ "66 na \n",
+ "67 żądanie \n",
+ "68 < \n",
+ "69 unk \n",
+ "70 > \n",
+ "71 < \n",
+ "72 unk \n",
+ "73 > \n",
+ "74 < \n",
+ "75 unk \n",
+ "76 > \n",
+ "77 wielbłądy \n",
+ "78 siÄ™ \n",
+ "79 toczy \n",
+ "80 na \n",
+ "81 most \n",
+ "82 siekierkowski \n",
+ "83 to \n",
+ "84 trud \n",
+ "85 i \n",
+ "86 czytanek \n",
+ "87 \n",
+ "88 pieszczoty \n",
+ "89 siÄ™ \n",
+ "90 trzy \n",
+ "91 płaczesz \n",
+ "92 tak \n",
+ "93 naprawdÄ™ \n",
+ "94 \n",
+ "95 może \n",
+ "96 kierkowski \n",
+ "97 to \n",
+ "98 zacznÄ… \n",
+ "99 \n",
+ "100 \n",
+ "101 siekierki \n",
+ "102 \n",
+ "103 sanktuarium \n",
+ "104 w \n",
+ "105 lourdes \n",
+ "106 siÄ™ \n",
+ "107 tym \n",
+ "108 przejęty \n",
+ "109 przystanku \n",
+ "110 który \n",
+ "111 torresie \n",
+ "112 \n",
+ "113 \n",
+ "114 czne \n",
+ "115 edition \n",
+ "116 - \n",
+ "117 czyli \n",
+ "118 to \n",
+ "119 wspólny \n",
+ "120 przystanek \n",
+ "121 małe \n",
+ "122 siekierki \n",
+ "123 ale \n",
+ "124 to \n",
+ "125 nie \n",
+ "126 \n",
+ "127 \n",
+ "128 \n",
+ "129 \n",
+ "130 \n",
+ "131 do \n",
+ "132 \n",
+ "133 końca \n",
+ "134 dotrzymać \n",
+ "135 dziÅ› \n",
+ "136 \n",
+ "137 \n",
+ "138 sÄ… \n",
+ "139 czternastej \n",
+ "140 czterdzieści \n",
+ "141 sześć \n",
+ "142 piętnasto \n",
+ "143 żeruje \n",
+ "144 a \n",
+ "145 nowy \n",
+ "146 gen \n",
+ "147 \n",
+ "148 \n",
+ "149 \n",
+ "150 \n",
+ "151 \n",
+ "152 . \n",
+ "153 "
]
},
"metadata": {},
@@ -7412,9 +7880,7 @@
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>step_type</th>\n",
- " <th>reference_word_pos</th>\n",
" <th>reference_word_text</th>\n",
- " <th>hypothesis_word_pos</th>\n",
" <th>hypothesis_word_text</th>\n",
" </tr>\n",
" </thead>\n",
@@ -7422,3729 +7888,2012 @@
" <tr>\n",
" <th>0</th>\n",
" <td>DELETION</td>\n",
- " <td>PRON</td>\n",
" <td>xxx</td>\n",
" <td></td>\n",
- " <td></td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>DELETION</td>\n",
- " <td>NOUN</td>\n",
" <td>dzień</td>\n",
" <td></td>\n",
- " <td></td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
- " <td>CORRECT</td>\n",
- " <td>ADJ</td>\n",
+ " <td>DELETION</td>\n",
" <td>dobry</td>\n",
- " <td>ADJ</td>\n",
- " <td>niedobre</td>\n",
+ " <td></td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>SUBSTITUTION</td>\n",
- " <td>NOUN</td>\n",
" <td>dzień</td>\n",
- " <td>X</td>\n",
- " <td>n</td>\n",
+ " <td>dobre</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>SUBSTITUTION</td>\n",
- " <td>ADJ</td>\n",
" <td>dobry</td>\n",
- " <td>PUNCT</td>\n",
- " <td>.</td>\n",
+ " <td>dyrektor</td>\n",
" </tr>\n",
" <tr>\n",
" <th>5</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>VERB</td>\n",
+ " <td>CORRECT</td>\n",
+ " <td>proszÄ™</td>\n",
" <td>proszÄ™</td>\n",
- " <td>X</td>\n",
- " <td>e</td>\n",
" </tr>\n",
" <tr>\n",
" <th>6</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>NOUN</td>\n",
+ " <td>DELETION</td>\n",
" <td>pana</td>\n",
- " <td>PUNCT</td>\n",
- " <td>.</td>\n",
+ " <td></td>\n",
" </tr>\n",
" <tr>\n",
" <th>7</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>PRON</td>\n",
+ " <td>DELETION</td>\n",
" <td>ja</td>\n",
- " <td>NOUN</td>\n",
- " <td>pracy</td>\n",
+ " <td></td>\n",
" </tr>\n",
" <tr>\n",
" <th>8</th>\n",
" <td>SUBSTITUTION</td>\n",
- " <td>VERB</td>\n",
- " <td>chciałam</td>\n",
- " <td>CCONJ</td>\n",
- " <td>a</td>\n",
+ " <td>mam</td>\n",
+ " <td>wybaczyć</td>\n",
" </tr>\n",
" <tr>\n",
" <th>9</th>\n",
- " <td>CORRECT</td>\n",
- " <td>PRON</td>\n",
- " <td>siÄ™</td>\n",
- " <td>PRON</td>\n",
- " <td>to</td>\n",
+ " <td>SUBSTITUTION</td>\n",
+ " <td>o</td>\n",
+ " <td>tryb</td>\n",
" </tr>\n",
" <tr>\n",
" <th>10</th>\n",
- " <td>DELETION</td>\n",
- " <td>VERB</td>\n",
- " <td>dowiedzieć</td>\n",
- " <td></td>\n",
- " <td></td>\n",
+ " <td>SUBSTITUTION</td>\n",
+ " <td>której</td>\n",
+ " <td>numer</td>\n",
" </tr>\n",
" <tr>\n",
" <th>11</th>\n",
" <td>SUBSTITUTION</td>\n",
- " <td>SCONJ</td>\n",
- " <td>bo</td>\n",
- " <td>ADV</td>\n",
- " <td>długo</td>\n",
+ " <td>będzie</td>\n",
+ " <td>jeden</td>\n",
" </tr>\n",
" <tr>\n",
" <th>12</th>\n",
- " <td>CORRECT</td>\n",
- " <td>PART</td>\n",
- " <td>nie</td>\n",
- " <td>PART</td>\n",
- " <td>nie</td>\n",
+ " <td>SUBSTITUTION</td>\n",
+ " <td>sto</td>\n",
+ " <td>to</td>\n",
" </tr>\n",
" <tr>\n",
" <th>13</th>\n",
" <td>SUBSTITUTION</td>\n",
- " <td>ADV</td>\n",
- " <td>bardzo</td>\n",
- " <td>AUX</td>\n",
- " <td>było</td>\n",
+ " <td>czterdzieści</td>\n",
+ " <td>teresie</td>\n",
" </tr>\n",
" <tr>\n",
" <th>14</th>\n",
" <td>SUBSTITUTION</td>\n",
- " <td>VERB</td>\n",
- " <td>wiem</td>\n",
- " <td>DET</td>\n",
- " <td>to</td>\n",
+ " <td>trzy</td>\n",
+ " <td>trzeba</td>\n",
" </tr>\n",
" <tr>\n",
" <th>15</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>ADV</td>\n",
- " <td>gdzie</td>\n",
- " <td>NOUN</td>\n",
- " <td>dziecko</td>\n",
+ " <td>CORRECT</td>\n",
+ " <td>będzie</td>\n",
+ " <td>będzie</td>\n",
" </tr>\n",
" <tr>\n",
" <th>16</th>\n",
" <td>CORRECT</td>\n",
- " <td>VERB</td>\n",
- " <td>znajduje</td>\n",
- " <td>VERB</td>\n",
- " <td>czuje</td>\n",
+ " <td>najbliższy</td>\n",
+ " <td>najbliższy</td>\n",
" </tr>\n",
" <tr>\n",
" <th>17</th>\n",
- " <td>CORRECT</td>\n",
- " <td>PRON</td>\n",
- " <td>siÄ™</td>\n",
- " <td>PRON</td>\n",
- " <td>siÄ™</td>\n",
+ " <td>SUBSTITUTION</td>\n",
+ " <td>z</td>\n",
+ " <td>ale</td>\n",
" </tr>\n",
" <tr>\n",
" <th>18</th>\n",
- " <td>DELETION</td>\n",
- " <td>NOUN</td>\n",
- " <td>ulica</td>\n",
- " <td></td>\n",
- " <td></td>\n",
+ " <td>SUBSTITUTION</td>\n",
+ " <td>Alei</td>\n",
+ " <td>i</td>\n",
" </tr>\n",
" <tr>\n",
" <th>19</th>\n",
- " <td>DELETION</td>\n",
- " <td>ADJ</td>\n",
- " <td>Zwierzyniecka</td>\n",
- " <td></td>\n",
- " <td></td>\n",
+ " <td>SUBSTITUTION</td>\n",
+ " <td>Alei</td>\n",
+ " <td>tu</td>\n",
" </tr>\n",
" <tr>\n",
" <th>20</th>\n",
- " <td>DELETION</td>\n",
- " <td>CCONJ</td>\n",
- " <td>i</td>\n",
- " <td></td>\n",
- " <td></td>\n",
+ " <td>SUBSTITUTION</td>\n",
+ " <td>Witosa</td>\n",
+ " <td>aleje</td>\n",
" </tr>\n",
" <tr>\n",
" <th>21</th>\n",
- " <td>CORRECT</td>\n",
- " <td>ADV</td>\n",
- " <td>jak</td>\n",
- " <td>ADV</td>\n",
- " <td>równie</td>\n",
+ " <td>SUBSTITUTION</td>\n",
+ " <td>w</td>\n",
+ " <td>pić</td>\n",
" </tr>\n",
" <tr>\n",
" <th>22</th>\n",
" <td>SUBSTITUTION</td>\n",
- " <td>VERB</td>\n",
- " <td>dojechać</td>\n",
- " <td>ADV</td>\n",
- " <td>szybko</td>\n",
+ " <td>stronÄ™</td>\n",
+ " <td>od</td>\n",
" </tr>\n",
" <tr>\n",
" <th>23</th>\n",
" <td>SUBSTITUTION</td>\n",
- " <td>ADP</td>\n",
- " <td>z</td>\n",
- " <td>SCONJ</td>\n",
- " <td>jak</td>\n",
+ " <td>Gocławia</td>\n",
+ " <td>roztropnego</td>\n",
" </tr>\n",
" <tr>\n",
" <th>24</th>\n",
" <td>SUBSTITUTION</td>\n",
- " <td>PROPN</td>\n",
- " <td>Bródna</td>\n",
- " <td>AUX</td>\n",
- " <td>to</td>\n",
+ " <td>z</td>\n",
+ " <td>działania</td>\n",
" </tr>\n",
" <tr>\n",
" <th>25</th>\n",
" <td>SUBSTITUTION</td>\n",
- " <td>ADP</td>\n",
- " <td>na</td>\n",
- " <td>NOUN</td>\n",
- " <td>cecha</td>\n",
+ " <td>tego</td>\n",
+ " <td>swego</td>\n",
" </tr>\n",
" <tr>\n",
" <th>26</th>\n",
- " <td>CORRECT</td>\n",
- " <td>NOUN</td>\n",
- " <td>przykład</td>\n",
- " <td>NOUN</td>\n",
- " <td>brud</td>\n",
+ " <td>SUBSTITUTION</td>\n",
+ " <td>przystanku</td>\n",
+ " <td>przystankom</td>\n",
" </tr>\n",
" <tr>\n",
" <th>27</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>PUNCT</td>\n",
- " <td>?</td>\n",
- " <td>DET</td>\n",
- " <td>ta</td>\n",
+ " <td>CORRECT</td>\n",
+ " <td>vis</td>\n",
+ " <td>vis</td>\n",
" </tr>\n",
" <tr>\n",
" <th>28</th>\n",
" <td>CORRECT</td>\n",
- " <td>ADP</td>\n",
- " <td>na</td>\n",
- " <td>ADP</td>\n",
- " <td>na</td>\n",
+ " <td>-</td>\n",
+ " <td>-</td>\n",
" </tr>\n",
" <tr>\n",
" <th>29</th>\n",
- " <td>INSERTION</td>\n",
- " <td></td>\n",
- " <td></td>\n",
- " <td>NOUN</td>\n",
- " <td>przykład</td>\n",
+ " <td>CORRECT</td>\n",
+ " <td>a</td>\n",
+ " <td>a</td>\n",
" </tr>\n",
" <tr>\n",
" <th>30</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>PROPN</td>\n",
- " <td>ZwierzynieckÄ…</td>\n",
- " <td>PRON</td>\n",
- " <td>siÄ™</td>\n",
+ " <td>CORRECT</td>\n",
+ " <td>-</td>\n",
+ " <td>-</td>\n",
" </tr>\n",
" <tr>\n",
" <th>31</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>ADP</td>\n",
- " <td>na</td>\n",
- " <td>ADV</td>\n",
- " <td>ostatnio</td>\n",
+ " <td>CORRECT</td>\n",
+ " <td>vis</td>\n",
+ " <td>vis</td>\n",
" </tr>\n",
" <tr>\n",
" <th>32</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>PROPN</td>\n",
- " <td>ZwierzynieckÄ…</td>\n",
- " <td>NOUN</td>\n",
- " <td>inżynierowie</td>\n",
+ " <td>INSERTION</td>\n",
+ " <td></td>\n",
+ " <td>zus</td>\n",
" </tr>\n",
" <tr>\n",
" <th>33</th>\n",
- " <td>CORRECT</td>\n",
- " <td>CCONJ</td>\n",
- " <td>a</td>\n",
- " <td>CCONJ</td>\n",
- " <td>i</td>\n",
+ " <td>INSERTION</td>\n",
+ " <td></td>\n",
+ " <td>-</td>\n",
" </tr>\n",
" <tr>\n",
" <th>34</th>\n",
" <td>SUBSTITUTION</td>\n",
- " <td>ADP</td>\n",
- " <td>z</td>\n",
- " <td>ADV</td>\n",
- " <td>brudno</td>\n",
+ " <td>ZUSu</td>\n",
+ " <td>u</td>\n",
" </tr>\n",
" <tr>\n",
" <th>35</th>\n",
" <td>SUBSTITUTION</td>\n",
- " <td>PROPN</td>\n",
- " <td>Bródna</td>\n",
- " <td>ADJ</td>\n",
- " <td>straszliwy</td>\n",
+ " <td>tak</td>\n",
+ " <td>to</td>\n",
" </tr>\n",
" <tr>\n",
" <th>36</th>\n",
" <td>SUBSTITUTION</td>\n",
- " <td>ADP</td>\n",
- " <td>z</td>\n",
- " <td>NOUN</td>\n",
- " <td>szok</td>\n",
+ " <td>?</td>\n",
+ " <td>jak</td>\n",
" </tr>\n",
" <tr>\n",
" <th>37</th>\n",
" <td>SUBSTITUTION</td>\n",
- " <td>DET</td>\n",
- " <td>którego</td>\n",
- " <td>ADJ</td>\n",
- " <td>brodatego</td>\n",
+ " <td>no</td>\n",
+ " <td>mnie</td>\n",
" </tr>\n",
" <tr>\n",
" <th>38</th>\n",
" <td>CORRECT</td>\n",
- " <td>NOUN</td>\n",
- " <td>miejsca</td>\n",
- " <td>NOUN</td>\n",
- " <td>ulica</td>\n",
+ " <td>nie</td>\n",
+ " <td>nie</td>\n",
" </tr>\n",
" <tr>\n",
" <th>39</th>\n",
" <td>SUBSTITUTION</td>\n",
- " <td>PUNCT</td>\n",
- " <td>?</td>\n",
- " <td>ADJ</td>\n",
- " <td>wyszogrodzka</td>\n",
+ " <td>nie</td>\n",
+ " <td><</td>\n",
" </tr>\n",
" <tr>\n",
" <th>40</th>\n",
- " <td>CORRECT</td>\n",
- " <td>ADP</td>\n",
- " <td>z</td>\n",
- " <td>ADP</td>\n",
- " <td>przy</td>\n",
+ " <td>SUBSTITUTION</td>\n",
+ " <td>tam</td>\n",
+ " <td>unk</td>\n",
" </tr>\n",
" <tr>\n",
" <th>41</th>\n",
- " <td>DELETION</td>\n",
- " <td>PROPN</td>\n",
- " <td>Bródna</td>\n",
- " <td></td>\n",
- " <td></td>\n",
+ " <td>SUBSTITUTION</td>\n",
+ " <td>vis</td>\n",
+ " <td>></td>\n",
" </tr>\n",
" <tr>\n",
" <th>42</th>\n",
- " <td>DELETION</td>\n",
- " <td>AUX</td>\n",
- " <td>to</td>\n",
- " <td></td>\n",
- " <td></td>\n",
+ " <td>SUBSTITUTION</td>\n",
+ " <td>-</td>\n",
+ " <td>widać</td>\n",
" </tr>\n",
" <tr>\n",
" <th>43</th>\n",
" <td>SUBSTITUTION</td>\n",
- " <td>AUX</td>\n",
- " <td>jest</td>\n",
- " <td>ADJ</td>\n",
- " <td>rembielińskiej</td>\n",
+ " <td>a</td>\n",
+ " <td><</td>\n",
" </tr>\n",
" <tr>\n",
" <th>44</th>\n",
" <td>SUBSTITUTION</td>\n",
- " <td>NOUN</td>\n",
- " <td>ulica</td>\n",
- " <td>PRON</td>\n",
- " <td>ich</td>\n",
+ " <td>-</td>\n",
+ " <td>unk</td>\n",
" </tr>\n",
" <tr>\n",
" <th>45</th>\n",
" <td>SUBSTITUTION</td>\n",
- " <td>PROPN</td>\n",
- " <td>Wyszogrodzka</td>\n",
- " <td>ADJ</td>\n",
- " <td>cztero</td>\n",
+ " <td>vis</td>\n",
+ " <td>></td>\n",
" </tr>\n",
" <tr>\n",
" <th>46</th>\n",
" <td>SUBSTITUTION</td>\n",
- " <td>ADV</td>\n",
- " <td>tu</td>\n",
- " <td>PART</td>\n",
- " <td>oto</td>\n",
+ " <td>Panoramy</td>\n",
+ " <td>panoramÄ™</td>\n",
" </tr>\n",
" <tr>\n",
" <th>47</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>ADP</td>\n",
- " <td>przy</td>\n",
- " <td>DET</td>\n",
- " <td>ta</td>\n",
+ " <td>CORRECT</td>\n",
+ " <td>przez</td>\n",
+ " <td>przez</td>\n",
" </tr>\n",
" <tr>\n",
" <th>48</th>\n",
" <td>SUBSTITUTION</td>\n",
- " <td>PROPN</td>\n",
- " <td>Rembielińskiej</td>\n",
- " <td>SCONJ</td>\n",
- " <td>jak</td>\n",
+ " <td>Siekierkowski</td>\n",
+ " <td>siekierko</td>\n",
" </tr>\n",
" <tr>\n",
" <th>49</th>\n",
" <td>SUBSTITUTION</td>\n",
- " <td>CCONJ</td>\n",
- " <td>czyli</td>\n",
- " <td>PART</td>\n",
- " <td>tak</td>\n",
+ " <td>tam</td>\n",
+ " <td>trwałego</td>\n",
" </tr>\n",
" <tr>\n",
" <th>50</th>\n",
" <td>SUBSTITUTION</td>\n",
- " <td>ADP</td>\n",
- " <td>przy</td>\n",
- " <td>DET</td>\n",
- " <td>dużo</td>\n",
+ " <td>w</td>\n",
+ " <td>tonÄ™</td>\n",
" </tr>\n",
" <tr>\n",
" <th>51</th>\n",
- " <td>CORRECT</td>\n",
- " <td>NOUN</td>\n",
- " <td>tramwajach</td>\n",
- " <td>NOUN</td>\n",
- " <td>punktów</td>\n",
+ " <td>SUBSTITUTION</td>\n",
+ " <td>stronÄ™</td>\n",
+ " <td>antoniego</td>\n",
" </tr>\n",
" <tr>\n",
" <th>52</th>\n",
- " <td>DELETION</td>\n",
- " <td>ADV</td>\n",
- " <td>tak</td>\n",
- " <td></td>\n",
- " <td></td>\n",
+ " <td>SUBSTITUTION</td>\n",
+ " <td>Gocławia</td>\n",
+ " <td>przystanki</td>\n",
" </tr>\n",
" <tr>\n",
" <th>53</th>\n",
- " <td>CORRECT</td>\n",
- " <td>PUNCT</td>\n",
- " <td>?</td>\n",
- " <td>PUNCT</td>\n",
- " <td><</td>\n",
+ " <td>SUBSTITUTION</td>\n",
+ " <td>ale</td>\n",
+ " <td>kolejowe</td>\n",
" </tr>\n",
" <tr>\n",
" <th>54</th>\n",
- " <td>DELETION</td>\n",
- " <td>ADP</td>\n",
- " <td>przy</td>\n",
- " <td></td>\n",
- " <td></td>\n",
+ " <td>CORRECT</td>\n",
+ " <td>to</td>\n",
+ " <td>to</td>\n",
" </tr>\n",
" <tr>\n",
" <th>55</th>\n",
" <td>DELETION</td>\n",
- " <td>NOUN</td>\n",
- " <td>tramwajach</td>\n",
- " <td></td>\n",
+ " <td>nie</td>\n",
" <td></td>\n",
" </tr>\n",
" <tr>\n",
" <th>56</th>\n",
" <td>DELETION</td>\n",
- " <td>ADV</td>\n",
- " <td>tak</td>\n",
- " <td></td>\n",
+ " <td>z</td>\n",
" <td></td>\n",
" </tr>\n",
" <tr>\n",
" <th>57</th>\n",
" <td>DELETION</td>\n",
- " <td>VERB</td>\n",
- " <td>może</td>\n",
- " <td></td>\n",
+ " <td>tego</td>\n",
" <td></td>\n",
" </tr>\n",
" <tr>\n",
" <th>58</th>\n",
- " <td>CORRECT</td>\n",
- " <td>NOUN</td>\n",
- " <td>pani</td>\n",
- " <td>NOUN</td>\n",
- " <td>unk</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>59</th>\n",
- " <td>DELETION</td>\n",
- " <td>VERB</td>\n",
- " <td>poczeka</td>\n",
- " <td></td>\n",
- " <td></td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>60</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>VERB</td>\n",
- " <td>sprawdzÄ™</td>\n",
- " <td>PUNCT</td>\n",
- " <td>></td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>61</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>ADV</td>\n",
- " <td>dobrze</td>\n",
- " <td>PRON</td>\n",
- " <td>oni</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>62</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>ADV</td>\n",
- " <td>dobrze</td>\n",
- " <td>SCONJ</td>\n",
- " <td>żeby</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>63</th>\n",
- " <td>CORRECT</td>\n",
- " <td>NOUN</td>\n",
- " <td>pani</td>\n",
- " <td>NOUN</td>\n",
- " <td>podróży</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>64</th>\n",
- " <td>DELETION</td>\n",
- " <td>PRON</td>\n",
- " <td>sobie</td>\n",
- " <td></td>\n",
- " <td></td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>65</th>\n",
- " <td>DELETION</td>\n",
- " <td>VERB</td>\n",
- " <td>podjedzie</td>\n",
- " <td></td>\n",
- " <td></td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>66</th>\n",
- " <td>CORRECT</td>\n",
- " <td>NOUN</td>\n",
- " <td>tramwajem</td>\n",
- " <td>NOUN</td>\n",
- " <td>tramwajem</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>67</th>\n",
- " <td>CORRECT</td>\n",
- " <td>ADP</td>\n",
- " <td>do</td>\n",
- " <td>ADP</td>\n",
- " <td>do</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>68</th>\n",
- " <td>CORRECT</td>\n",
- " <td>NOUN</td>\n",
- " <td>Ronda</td>\n",
- " <td>NOUN</td>\n",
- " <td>rondo</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>69</th>\n",
- " <td>CORRECT</td>\n",
- " <td>PROPN</td>\n",
- " <td>Żaba</td>\n",
- " <td>PROPN</td>\n",
- " <td>Żaba</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>70</th>\n",
" <td>DELETION</td>\n",
- " <td>ADV</td>\n",
- " <td>tak</td>\n",
- " <td></td>\n",
+ " <td>przystanku</td>\n",
" <td></td>\n",
" </tr>\n",
" <tr>\n",
- " <th>71</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>ADP</td>\n",
- " <td>od</td>\n",
- " <td>PUNCT</td>\n",
- " <td><</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>72</th>\n",
- " <td>CORRECT</td>\n",
- " <td>NOUN</td>\n",
- " <td>Ronda</td>\n",
- " <td>NOUN</td>\n",
- " <td>unk</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>73</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>PROPN</td>\n",
- " <td>Żaba</td>\n",
- " <td>PUNCT</td>\n",
- " <td>></td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>74</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>PART</td>\n",
- " <td>już</td>\n",
- " <td>NOUN</td>\n",
- " <td>toronto</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>75</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>NUM</td>\n",
- " <td>sto</td>\n",
- " <td>PART</td>\n",
- " <td>już</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>76</th>\n",
- " <td>CORRECT</td>\n",
- " <td>NUM</td>\n",
- " <td>sześćdziesiąt</td>\n",
- " <td>NUM</td>\n",
- " <td>sto</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>77</th>\n",
- " <td>CORRECT</td>\n",
- " <td>NUM</td>\n",
- " <td>dwa</td>\n",
- " <td>NUM</td>\n",
- " <td>sześćdziesiąt</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>78</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>AUX</td>\n",
- " <td>jest</td>\n",
- " <td>NOUN</td>\n",
- " <td>wojsk</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>79</th>\n",
- " <td>CORRECT</td>\n",
- " <td>NUM</td>\n",
- " <td>sto</td>\n",
- " <td>NUM</td>\n",
- " <td>sto</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>80</th>\n",
- " <td>CORRECT</td>\n",
- " <td>NUM</td>\n",
- " <td>sześćdziesiąt</td>\n",
- " <td>NUM</td>\n",
- " <td>sześćdziesiąt</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>81</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>NUM</td>\n",
- " <td>dwa</td>\n",
- " <td>DET</td>\n",
- " <td>ta</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>82</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>ADV</td>\n",
- " <td>tak</td>\n",
- " <td>PUNCT</td>\n",
- " <td><</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>83</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>CCONJ</td>\n",
- " <td>i</td>\n",
- " <td>NOUN</td>\n",
- " <td>unk</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>84</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>NUM</td>\n",
- " <td>sto</td>\n",
- " <td>PUNCT</td>\n",
- " <td>></td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>85</th>\n",
- " <td>CORRECT</td>\n",
- " <td>NUM</td>\n",
- " <td>sześćdziesiąt</td>\n",
- " <td>NUM</td>\n",
- " <td>trzysta</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>86</th>\n",
- " <td>CORRECT</td>\n",
- " <td>NUM</td>\n",
- " <td>dwa</td>\n",
- " <td>NUM</td>\n",
- " <td>sześćdziesiąt</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>87</th>\n",
+ " <th>59</th>\n",
" <td>DELETION</td>\n",
- " <td>ADV</td>\n",
- " <td>tam</td>\n",
- " <td></td>\n",
- " <td></td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>88</th>\n",
- " <td>CORRECT</td>\n",
- " <td>VERB</td>\n",
- " <td>dojadÄ™</td>\n",
- " <td>VERB</td>\n",
- " <td>rataja</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>89</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>ADP</td>\n",
- " <td>do</td>\n",
- " <td>PUNCT</td>\n",
- " <td><</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>90</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>DET</td>\n",
- " <td>tej</td>\n",
- " <td>NOUN</td>\n",
- " <td>unk</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>91</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>NOUN</td>\n",
- " <td>ulicy</td>\n",
- " <td>PUNCT</td>\n",
- " <td>></td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>92</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>ADV</td>\n",
- " <td>tak</td>\n",
- " <td>DET</td>\n",
- " <td>tej</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>93</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>VERB</td>\n",
- " <td>może</td>\n",
- " <td>PUNCT</td>\n",
- " <td><</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>94</th>\n",
- " <td>CORRECT</td>\n",
- " <td>NOUN</td>\n",
- " <td>pani</td>\n",
- " <td>NOUN</td>\n",
- " <td>unk</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>95</th>\n",
- " <td>INSERTION</td>\n",
- " <td></td>\n",
- " <td></td>\n",
- " <td>PUNCT</td>\n",
- " <td>></td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>96</th>\n",
- " <td>CORRECT</td>\n",
- " <td>VERB</td>\n",
- " <td>wysiąść</td>\n",
- " <td>VERB</td>\n",
- " <td>może</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>97</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>ADP</td>\n",
- " <td>na</td>\n",
- " <td>VERB</td>\n",
- " <td>pojawić</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>98</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>NOUN</td>\n",
- " <td>przystanku</td>\n",
- " <td>PRON</td>\n",
- " <td>siÄ™</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>99</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>PROPN</td>\n",
- " <td>Bartycka</td>\n",
- " <td>NUM</td>\n",
- " <td>trzy</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>100</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>CCONJ</td>\n",
- " <td>albo</td>\n",
- " <td>ADV</td>\n",
- " <td>stÄ…d</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>101</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>PROPN</td>\n",
- " <td>Sielce</td>\n",
- " <td>PUNCT</td>\n",
- " <td><</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>102</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>PROPN</td>\n",
- " <td>Bartycka</td>\n",
- " <td>X</td>\n",
- " <td>unk</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>103</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>CCONJ</td>\n",
- " <td>albo</td>\n",
- " <td>PUNCT</td>\n",
- " <td>></td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>104</th>\n",
- " <td>CORRECT</td>\n",
- " <td>PUNCT</td>\n",
- " <td>?</td>\n",
- " <td>PUNCT</td>\n",
- " <td><</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>105</th>\n",
- " <td>CORRECT</td>\n",
- " <td>PROPN</td>\n",
- " <td>Sielce</td>\n",
- " <td>PROPN</td>\n",
- " <td>unk</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>106</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>PROPN</td>\n",
- " <td>Sielce</td>\n",
- " <td>PUNCT</td>\n",
- " <td>></td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>107</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>ADV</td>\n",
- " <td>tak</td>\n",
- " <td>PUNCT</td>\n",
- " <td><</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>108</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>PUNCT</td>\n",
- " <td>?</td>\n",
- " <td>PROPN</td>\n",
- " <td>unk</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>109</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>ADV</td>\n",
- " <td>tak</td>\n",
- " <td>PUNCT</td>\n",
- " <td>></td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>110</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>X</td>\n",
- " <td>aha</td>\n",
- " <td>PUNCT</td>\n",
- " <td><</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>111</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>CCONJ</td>\n",
- " <td>i</td>\n",
- " <td>PROPN</td>\n",
- " <td>unk</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>112</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>ADV</td>\n",
- " <td>tam</td>\n",
- " <td>PUNCT</td>\n",
- " <td>></td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>113</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>ADP</td>\n",
- " <td>w</td>\n",
- " <td>PUNCT</td>\n",
- " <td><</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>114</th>\n",
- " <td>CORRECT</td>\n",
- " <td>NOUN</td>\n",
- " <td>pobliżu</td>\n",
- " <td>NOUN</td>\n",
- " <td>unk</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>115</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>AUX</td>\n",
- " <td>jest</td>\n",
- " <td>PUNCT</td>\n",
- " <td>></td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>116</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>DET</td>\n",
- " <td>ta</td>\n",
- " <td>NOUN</td>\n",
- " <td>berty</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>117</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>NOUN</td>\n",
- " <td>ulica</td>\n",
- " <td>ADV</td>\n",
- " <td>coraz</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>118</th>\n",
- " <td>CORRECT</td>\n",
- " <td>ADV</td>\n",
- " <td>tak</td>\n",
- " <td>ADV</td>\n",
- " <td>szybciej</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>119</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>PUNCT</td>\n",
- " <td>?</td>\n",
- " <td>ADJ</td>\n",
- " <td>bartycka</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>120</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>CCONJ</td>\n",
- " <td>a</td>\n",
- " <td>PUNCT</td>\n",
- " <td><</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>121</th>\n",
- " <td>CORRECT</td>\n",
- " <td>NOUN</td>\n",
- " <td>Zwierzyniecka</td>\n",
- " <td>NOUN</td>\n",
- " <td>unk</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>122</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>ADJ</td>\n",
- " <td>wysoki</td>\n",
- " <td>PUNCT</td>\n",
- " <td>></td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>123</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>NOUN</td>\n",
- " <td>numer</td>\n",
- " <td>NUM</td>\n",
- " <td>trzema</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>124</th>\n",
- " <td>CORRECT</td>\n",
- " <td>VERB</td>\n",
- " <td>ma</td>\n",
- " <td>VERB</td>\n",
- " <td>trzeba</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>125</th>\n",
- " <td>DELETION</td>\n",
- " <td>NOUN</td>\n",
- " <td>pani</td>\n",
- " <td></td>\n",
- " <td></td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>126</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>PUNCT</td>\n",
- " <td>?</td>\n",
- " <td>PRON</td>\n",
- " <td>siÄ™</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>127</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>PROPN</td>\n",
- " <td>Zwierzyniecka</td>\n",
- " <td>ADV</td>\n",
- " <td>trochÄ™</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>128</th>\n",
- " <td>CORRECT</td>\n",
- " <td>ADV</td>\n",
- " <td>zaraz</td>\n",
- " <td>ADV</td>\n",
- " <td>tak</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>129</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>NOUN</td>\n",
- " <td>momencik</td>\n",
- " <td>SCONJ</td>\n",
- " <td>jak</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>130</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>NUM</td>\n",
- " <td>osiem</td>\n",
- " <td>CCONJ</td>\n",
- " <td>i</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>131</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>CCONJ</td>\n",
- " <td>A</td>\n",
- " <td>DET</td>\n",
- " <td>te</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>132</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>PROPN</td>\n",
- " <td>Zwierzyniecka</td>\n",
- " <td>NOUN</td>\n",
- " <td>plany</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>133</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>AUX</td>\n",
- " <td>to</td>\n",
- " <td>VERB</td>\n",
- " <td>stały</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>134</th>\n",
- " <td>CORRECT</td>\n",
- " <td>PRON</td>\n",
- " <td>to</td>\n",
- " <td>PRON</td>\n",
- " <td>siÄ™</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>135</th>\n",
- " <td>INSERTION</td>\n",
- " <td></td>\n",
- " <td></td>\n",
- " <td>ADJ</td>\n",
- " <td>słynne</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>136</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>ADP</td>\n",
- " <td>przy</td>\n",
- " <td>ADV</td>\n",
- " <td>ciężko</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>137</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>PROPN</td>\n",
- " <td>Sielce</td>\n",
- " <td>VERB</td>\n",
- " <td>dyszÄ…c</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>138</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>NOUN</td>\n",
- " <td>trza</td>\n",
- " <td>CCONJ</td>\n",
- " <td>i</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>139</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>VERB</td>\n",
- " <td>wysiąść</td>\n",
- " <td>NOUN</td>\n",
- " <td>numer</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>140</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>ADP</td>\n",
- " <td>przy</td>\n",
- " <td>ADJ</td>\n",
- " <td>ewidencyjny</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>141</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>PROPN</td>\n",
- " <td>Sielce</td>\n",
- " <td>PUNCT</td>\n",
- " <td><</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>142</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>ADV</td>\n",
- " <td>tak</td>\n",
- " <td>NOUN</td>\n",
- " <td>unk</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>143</th>\n",
- " <td>CORRECT</td>\n",
- " <td>PUNCT</td>\n",
- " <td>?</td>\n",
- " <td>PUNCT</td>\n",
- " <td>></td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>144</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>ADV</td>\n",
- " <td>tak</td>\n",
- " <td>ADJ</td>\n",
- " <td>nowy</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>145</th>\n",
- " <td>CORRECT</td>\n",
- " <td>NOUN</td>\n",
- " <td>przystanek</td>\n",
- " <td>NOUN</td>\n",
- " <td>typ</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>146</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>PROPN</td>\n",
- " <td>Sielce</td>\n",
- " <td>PUNCT</td>\n",
- " <td><</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>147</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>X</td>\n",
- " <td>aha</td>\n",
- " <td>NOUN</td>\n",
- " <td>unk</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>148</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>ADV</td>\n",
- " <td>tak</td>\n",
- " <td>PUNCT</td>\n",
- " <td>></td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>149</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>PART</td>\n",
- " <td>no</td>\n",
- " <td>PUNCT</td>\n",
- " <td>-</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>150</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>ADV</td>\n",
- " <td>dobrze</td>\n",
- " <td>PRON</td>\n",
- " <td>siÄ™</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>151</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>CCONJ</td>\n",
- " <td>a</td>\n",
- " <td>PUNCT</td>\n",
- " <td>-</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>152</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>PROPN</td>\n",
- " <td>Sielce</td>\n",
- " <td>ADP</td>\n",
- " <td>dla</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>153</th>\n",
- " <td>CORRECT</td>\n",
- " <td>PRON</td>\n",
- " <td>to</td>\n",
- " <td>PRON</td>\n",
- " <td>mnie</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>154</th>\n",
- " <td>CORRECT</td>\n",
- " <td>VERB</td>\n",
- " <td>znaczy</td>\n",
- " <td>VERB</td>\n",
- " <td>trwało</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>155</th>\n",
- " <td>DELETION</td>\n",
- " <td>DET</td>\n",
- " <td>jaka</td>\n",
- " <td></td>\n",
- " <td></td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>156</th>\n",
- " <td>CORRECT</td>\n",
- " <td>AUX</td>\n",
- " <td>to</td>\n",
- " <td>AUX</td>\n",
- " <td>to</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>157</th>\n",
- " <td>DELETION</td>\n",
- " <td>PART</td>\n",
- " <td>już</td>\n",
- " <td></td>\n",
- " <td></td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>158</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>AUX</td>\n",
- " <td>jest</td>\n",
- " <td>NUM</td>\n",
- " <td>trzy</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>159</th>\n",
- " <td>CORRECT</td>\n",
- " <td>NOUN</td>\n",
- " <td>dzielnica</td>\n",
- " <td>NOUN</td>\n",
- " <td>trzody</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>160</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>AUX</td>\n",
- " <td>to</td>\n",
- " <td>ADJ</td>\n",
- " <td>ścięte</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>161</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>DET</td>\n",
- " <td>ta</td>\n",
- " <td>NOUN</td>\n",
- " <td>tato</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>162</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>AUX</td>\n",
- " <td>jest</td>\n",
- " <td>ADJ</td>\n",
- " <td>taneczne</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>163</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>ADP</td>\n",
- " <td>przy</td>\n",
- " <td>PUNCT</td>\n",
- " <td><</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>164</th>\n",
- " <td>CORRECT</td>\n",
- " <td>NOUN</td>\n",
- " <td>ulica</td>\n",
- " <td>NOUN</td>\n",
- " <td>unk</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>165</th>\n",
- " <td>DELETION</td>\n",
- " <td>PROPN</td>\n",
- " <td>Gagarina</td>\n",
- " <td></td>\n",
- " <td></td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>166</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>CCONJ</td>\n",
- " <td>a</td>\n",
- " <td>PUNCT</td>\n",
- " <td>></td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>167</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>ADP</td>\n",
- " <td>przy</td>\n",
- " <td>DET</td>\n",
- " <td>ta</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>168</th>\n",
- " <td>CORRECT</td>\n",
- " <td>NOUN</td>\n",
- " <td>ulicy</td>\n",
- " <td>NOUN</td>\n",
- " <td>notatka</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>169</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>PROPN</td>\n",
- " <td>Gagarina</td>\n",
- " <td>PRON</td>\n",
- " <td>siÄ™</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>170</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>CCONJ</td>\n",
- " <td>czyli</td>\n",
- " <td>ADV</td>\n",
- " <td>tutaj</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>171</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>PRON</td>\n",
- " <td>to</td>\n",
- " <td>PART</td>\n",
- " <td>także</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>172</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>AUX</td>\n",
- " <td>jest</td>\n",
- " <td>DET</td>\n",
- " <td>kilka</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>173</th>\n",
- " <td>CORRECT</td>\n",
- " <td>ADV</td>\n",
- " <td>tam</td>\n",
- " <td>ADV</td>\n",
- " <td>tutaj</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>174</th>\n",
- " <td>INSERTION</td>\n",
- " <td></td>\n",
- " <td></td>\n",
- " <td>NUM</td>\n",
- " <td>trzy</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>175</th>\n",
- " <td>INSERTION</td>\n",
- " <td></td>\n",
- " <td></td>\n",
- " <td>CCONJ</td>\n",
- " <td>czy</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>176</th>\n",
- " <td>INSERTION</td>\n",
- " <td></td>\n",
- " <td></td>\n",
- " <td>NUM</td>\n",
- " <td>cztery</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>177</th>\n",
- " <td>CORRECT</td>\n",
- " <td>NOUN</td>\n",
- " <td>Mokotów</td>\n",
- " <td>NOUN</td>\n",
- " <td>dni</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>178</th>\n",
- " <td>INSERTION</td>\n",
- " <td></td>\n",
- " <td></td>\n",
- " <td>PUNCT</td>\n",
- " <td><</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>179</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>ADP</td>\n",
- " <td>po</td>\n",
- " <td>NOUN</td>\n",
- " <td>unk</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>180</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>ADJ</td>\n",
- " <td>prostu</td>\n",
- " <td>PUNCT</td>\n",
- " <td>></td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>181</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>ADV</td>\n",
- " <td>tak</td>\n",
- " <td>NOUN</td>\n",
- " <td>płyty</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>182</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>PUNCT</td>\n",
- " <td>?</td>\n",
- " <td>NOUN</td>\n",
- " <td>darin</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>183</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>ADV</td>\n",
- " <td>tak</td>\n",
- " <td>ADJ</td>\n",
- " <td>nakryta</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>184</th>\n",
- " <td>CORRECT</td>\n",
- " <td>NOUN</td>\n",
- " <td>Siekierki</td>\n",
- " <td>NOUN</td>\n",
- " <td>plakatów</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>185</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>PROPN</td>\n",
- " <td>Mokotów</td>\n",
- " <td>ADP</td>\n",
- " <td>pod</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>186</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>CCONJ</td>\n",
- " <td>a</td>\n",
- " <td>NOUN</td>\n",
- " <td>hutach</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>187</th>\n",
- " <td>CORRECT</td>\n",
- " <td>NOUN</td>\n",
- " <td>Siekierki</td>\n",
- " <td>NOUN</td>\n",
- " <td>siekierkowskÄ…</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>188</th>\n",
- " <td>INSERTION</td>\n",
- " <td></td>\n",
- " <td></td>\n",
- " <td>PUNCT</td>\n",
- " <td><</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>189</th>\n",
- " <td>CORRECT</td>\n",
- " <td>PROPN</td>\n",
- " <td>Mokotów</td>\n",
- " <td>PROPN</td>\n",
- " <td>unk</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>190</th>\n",
- " <td>INSERTION</td>\n",
- " <td></td>\n",
- " <td></td>\n",
- " <td>PUNCT</td>\n",
- " <td>></td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>191</th>\n",
- " <td>CORRECT</td>\n",
- " <td>CCONJ</td>\n",
- " <td>i</td>\n",
- " <td>CCONJ</td>\n",
- " <td>a</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>192</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>ADV</td>\n",
- " <td>tam</td>\n",
- " <td>NOUN</td>\n",
- " <td>siekierki</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>193</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>SCONJ</td>\n",
- " <td>jak</td>\n",
- " <td>ADJ</td>\n",
- " <td>hoszowski</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>194</th>\n",
- " <td>CORRECT</td>\n",
- " <td>NOUN</td>\n",
- " <td>pani</td>\n",
- " <td>NOUN</td>\n",
- " <td>czytelnik</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>195</th>\n",
- " <td>CORRECT</td>\n",
- " <td>VERB</td>\n",
- " <td>wysiÄ…dzie</td>\n",
- " <td>VERB</td>\n",
- " <td>wyszedł</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>196</th>\n",
- " <td>INSERTION</td>\n",
- " <td></td>\n",
- " <td></td>\n",
- " <td>ADP</td>\n",
- " <td>od</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>197</th>\n",
- " <td>CORRECT</td>\n",
- " <td>DET</td>\n",
- " <td>to</td>\n",
- " <td>DET</td>\n",
- " <td>swoich</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>198</th>\n",
- " <td>CORRECT</td>\n",
- " <td>NOUN</td>\n",
- " <td>trza</td>\n",
- " <td>NOUN</td>\n",
- " <td>kolegów</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>199</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>VERB</td>\n",
- " <td>wejść</td>\n",
- " <td>NOUN</td>\n",
- " <td>uliczek</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>200</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>ADP</td>\n",
- " <td>w</td>\n",
- " <td>PUNCT</td>\n",
- " <td><</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>201</th>\n",
- " <td>CORRECT</td>\n",
- " <td>NOUN</td>\n",
- " <td>lewo</td>\n",
- " <td>NOUN</td>\n",
- " <td>unk</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>202</th>\n",
- " <td>INSERTION</td>\n",
- " <td></td>\n",
- " <td></td>\n",
- " <td>PUNCT</td>\n",
- " <td>></td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>203</th>\n",
- " <td>CORRECT</td>\n",
- " <td>ADP</td>\n",
- " <td>w</td>\n",
- " <td>ADP</td>\n",
- " <td>od</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>204</th>\n",
- " <td>INSERTION</td>\n",
- " <td></td>\n",
- " <td></td>\n",
- " <td>PUNCT</td>\n",
- " <td><</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>205</th>\n",
- " <td>CORRECT</td>\n",
- " <td>NOUN</td>\n",
- " <td>ulicÄ™</td>\n",
- " <td>NOUN</td>\n",
- " <td>unk</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>206</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>PROPN</td>\n",
- " <td>Nehru</td>\n",
- " <td>PUNCT</td>\n",
- " <td>></td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>207</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>CCONJ</td>\n",
- " <td>i</td>\n",
- " <td>VERB</td>\n",
- " <td>odchodzi</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>208</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>ADP</td>\n",
- " <td>od</td>\n",
- " <td>VERB</td>\n",
- " <td>służy</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>209</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>PROPN</td>\n",
- " <td>Nehru</td>\n",
- " <td>CCONJ</td>\n",
- " <td>nie</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>210</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>VERB</td>\n",
- " <td>odchodzi</td>\n",
- " <td>CCONJ</td>\n",
- " <td>tylko</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>211</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>ADJ</td>\n",
- " <td>Zwierzyniecka</td>\n",
- " <td>PUNCT</td>\n",
- " <td><</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>212</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>ADP</td>\n",
- " <td>w</td>\n",
- " <td>PROPN</td>\n",
- " <td>unk</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>213</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>ADV</td>\n",
- " <td>lewo</td>\n",
- " <td>PUNCT</td>\n",
- " <td>></td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>214</th>\n",
- " <td>CORRECT</td>\n",
- " <td>ADP</td>\n",
- " <td>w</td>\n",
- " <td>ADP</td>\n",
- " <td>na</td>\n",
+ " <td>Aleja</td>\n",
+ " <td></td>\n",
" </tr>\n",
" <tr>\n",
- " <th>215</th>\n",
+ " <th>60</th>\n",
" <td>DELETION</td>\n",
- " <td>ADV</td>\n",
- " <td>lewo</td>\n",
- " <td></td>\n",
+ " <td>Witosa</td>\n",
" <td></td>\n",
" </tr>\n",
" <tr>\n",
- " <th>216</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>CCONJ</td>\n",
- " <td>i</td>\n",
- " <td>NOUN</td>\n",
- " <td>ulicach</td>\n",
+ " <th>61</th>\n",
+ " <td>DELETION</td>\n",
+ " <td>?</td>\n",
+ " <td></td>\n",
" </tr>\n",
" <tr>\n",
- " <th>217</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>NOUN</td>\n",
- " <td>ulica</td>\n",
- " <td>PUNCT</td>\n",
- " <td><</td>\n",
+ " <th>62</th>\n",
+ " <td>DELETION</td>\n",
+ " <td>no</td>\n",
+ " <td></td>\n",
" </tr>\n",
" <tr>\n",
- " <th>218</th>\n",
+ " <th>63</th>\n",
" <td>SUBSTITUTION</td>\n",
- " <td>PROPN</td>\n",
- " <td>Nehru</td>\n",
- " <td>X</td>\n",
- " <td>unk</td>\n",
+ " <td>to</td>\n",
+ " <td>było</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>219</th>\n",
- " <td>CORRECT</td>\n",
- " <td>PUNCT</td>\n",
- " <td>?</td>\n",
- " <td>PUNCT</td>\n",
- " <td>></td>\n",
+ " <th>64</th>\n",
+ " <td>SUBSTITUTION</td>\n",
+ " <td>jest</td>\n",
+ " <td>coÅ›</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>220</th>\n",
+ " <th>65</th>\n",
" <td>CORRECT</td>\n",
- " <td>ADV</td>\n",
- " <td>tak</td>\n",
- " <td>ADV</td>\n",
- " <td>tak</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>221</th>\n",
- " <td>DELETION</td>\n",
- " <td>PROPN</td>\n",
- " <td>Nehru</td>\n",
- " <td></td>\n",
- " <td></td>\n",
+ " <td>czy</td>\n",
+ " <td>czy</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>222</th>\n",
+ " <th>66</th>\n",
" <td>SUBSTITUTION</td>\n",
- " <td>ADV</td>\n",
- " <td>dobrze</td>\n",
- " <td>NOUN</td>\n",
- " <td>numeru</td>\n",
+ " <td>Bartoszka</td>\n",
+ " <td>bartoszka</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>223</th>\n",
+ " <th>67</th>\n",
" <td>CORRECT</td>\n",
- " <td>VERB</td>\n",
- " <td>dziękuję</td>\n",
- " <td>VERB</td>\n",
- " <td>krytykuje</td>\n",
+ " <td>na</td>\n",
+ " <td>na</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>224</th>\n",
+ " <th>68</th>\n",
" <td>CORRECT</td>\n",
- " <td>NOUN</td>\n",
- " <td>panu</td>\n",
- " <td>NOUN</td>\n",
- " <td>pan</td>\n",
+ " <td>żądanie</td>\n",
+ " <td>żądanie</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>225</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>ADV</td>\n",
- " <td>bardzo</td>\n",
- " <td>PUNCT</td>\n",
+ " <th>69</th>\n",
+ " <td>INSERTION</td>\n",
+ " <td></td>\n",
" <td><</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>226</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>VERB</td>\n",
- " <td>proszÄ™</td>\n",
- " <td>PROPN</td>\n",
+ " <th>70</th>\n",
+ " <td>INSERTION</td>\n",
+ " <td></td>\n",
" <td>unk</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>227</th>\n",
+ " <th>71</th>\n",
" <td>SUBSTITUTION</td>\n",
- " <td>ADP</td>\n",
- " <td>do</td>\n",
- " <td>PUNCT</td>\n",
+ " <td>wie</td>\n",
" <td>></td>\n",
" </tr>\n",
" <tr>\n",
- " <th>228</th>\n",
- " <td>CORRECT</td>\n",
- " <td>NOUN</td>\n",
- " <td>widzenia</td>\n",
- " <td>NOUN</td>\n",
- " <td>badania</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>229</th>\n",
+ " <th>72</th>\n",
" <td>SUBSTITUTION</td>\n",
- " <td>ADP</td>\n",
- " <td>do</td>\n",
- " <td>PUNCT</td>\n",
+ " <td>pan</td>\n",
" <td><</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>230</th>\n",
- " <td>CORRECT</td>\n",
- " <td>NOUN</td>\n",
- " <td>widzenia</td>\n",
- " <td>NOUN</td>\n",
+ " <th>73</th>\n",
+ " <td>SUBSTITUTION</td>\n",
+ " <td>gdzie</td>\n",
" <td>unk</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>231</th>\n",
- " <td>INSERTION</td>\n",
- " <td></td>\n",
- " <td></td>\n",
- " <td>PUNCT</td>\n",
+ " <th>74</th>\n",
+ " <td>SUBSTITUTION</td>\n",
+ " <td>jest</td>\n",
" <td>></td>\n",
" </tr>\n",
" <tr>\n",
- " <th>232</th>\n",
- " <td>INSERTION</td>\n",
- " <td></td>\n",
- " <td></td>\n",
- " <td>SPACE</td>\n",
- " <td></td>\n",
- " </tr>\n",
- " </tbody>\n",
- "</table>\n",
- "</div>"
- ],
- "text/plain": [
- " step_type reference_word_pos reference_word_text hypothesis_word_pos \\\n",
- "0 DELETION PRON xxx \n",
- "1 DELETION NOUN dzień \n",
- "2 CORRECT ADJ dobry ADJ \n",
- "3 SUBSTITUTION NOUN dzień X \n",
- "4 SUBSTITUTION ADJ dobry PUNCT \n",
- "5 SUBSTITUTION VERB proszÄ™ X \n",
- "6 SUBSTITUTION NOUN pana PUNCT \n",
- "7 SUBSTITUTION PRON ja NOUN \n",
- "8 SUBSTITUTION VERB chciałam CCONJ \n",
- "9 CORRECT PRON siÄ™ PRON \n",
- "10 DELETION VERB dowiedzieć \n",
- "11 SUBSTITUTION SCONJ bo ADV \n",
- "12 CORRECT PART nie PART \n",
- "13 SUBSTITUTION ADV bardzo AUX \n",
- "14 SUBSTITUTION VERB wiem DET \n",
- "15 SUBSTITUTION ADV gdzie NOUN \n",
- "16 CORRECT VERB znajduje VERB \n",
- "17 CORRECT PRON siÄ™ PRON \n",
- "18 DELETION NOUN ulica \n",
- "19 DELETION ADJ Zwierzyniecka \n",
- "20 DELETION CCONJ i \n",
- "21 CORRECT ADV jak ADV \n",
- "22 SUBSTITUTION VERB dojechać ADV \n",
- "23 SUBSTITUTION ADP z SCONJ \n",
- "24 SUBSTITUTION PROPN Bródna AUX \n",
- "25 SUBSTITUTION ADP na NOUN \n",
- "26 CORRECT NOUN przykład NOUN \n",
- "27 SUBSTITUTION PUNCT ? DET \n",
- "28 CORRECT ADP na ADP \n",
- "29 INSERTION NOUN \n",
- "30 SUBSTITUTION PROPN ZwierzynieckÄ… PRON \n",
- "31 SUBSTITUTION ADP na ADV \n",
- "32 SUBSTITUTION PROPN ZwierzynieckÄ… NOUN \n",
- "33 CORRECT CCONJ a CCONJ \n",
- "34 SUBSTITUTION ADP z ADV \n",
- "35 SUBSTITUTION PROPN Bródna ADJ \n",
- "36 SUBSTITUTION ADP z NOUN \n",
- "37 SUBSTITUTION DET którego ADJ \n",
- "38 CORRECT NOUN miejsca NOUN \n",
- "39 SUBSTITUTION PUNCT ? ADJ \n",
- "40 CORRECT ADP z ADP \n",
- "41 DELETION PROPN Bródna \n",
- "42 DELETION AUX to \n",
- "43 SUBSTITUTION AUX jest ADJ \n",
- "44 SUBSTITUTION NOUN ulica PRON \n",
- "45 SUBSTITUTION PROPN Wyszogrodzka ADJ \n",
- "46 SUBSTITUTION ADV tu PART \n",
- "47 SUBSTITUTION ADP przy DET \n",
- "48 SUBSTITUTION PROPN Rembielińskiej SCONJ \n",
- "49 SUBSTITUTION CCONJ czyli PART \n",
- "50 SUBSTITUTION ADP przy DET \n",
- "51 CORRECT NOUN tramwajach NOUN \n",
- "52 DELETION ADV tak \n",
- "53 CORRECT PUNCT ? PUNCT \n",
- "54 DELETION ADP przy \n",
- "55 DELETION NOUN tramwajach \n",
- "56 DELETION ADV tak \n",
- "57 DELETION VERB może \n",
- "58 CORRECT NOUN pani NOUN \n",
- "59 DELETION VERB poczeka \n",
- "60 SUBSTITUTION VERB sprawdzÄ™ PUNCT \n",
- "61 SUBSTITUTION ADV dobrze PRON \n",
- "62 SUBSTITUTION ADV dobrze SCONJ \n",
- "63 CORRECT NOUN pani NOUN \n",
- "64 DELETION PRON sobie \n",
- "65 DELETION VERB podjedzie \n",
- "66 CORRECT NOUN tramwajem NOUN \n",
- "67 CORRECT ADP do ADP \n",
- "68 CORRECT NOUN Ronda NOUN \n",
- "69 CORRECT PROPN Żaba PROPN \n",
- "70 DELETION ADV tak \n",
- "71 SUBSTITUTION ADP od PUNCT \n",
- "72 CORRECT NOUN Ronda NOUN \n",
- "73 SUBSTITUTION PROPN Żaba PUNCT \n",
- "74 SUBSTITUTION PART już NOUN \n",
- "75 SUBSTITUTION NUM sto PART \n",
- "76 CORRECT NUM sześćdziesiąt NUM \n",
- "77 CORRECT NUM dwa NUM \n",
- "78 SUBSTITUTION AUX jest NOUN \n",
- "79 CORRECT NUM sto NUM \n",
- "80 CORRECT NUM sześćdziesiąt NUM \n",
- "81 SUBSTITUTION NUM dwa DET \n",
- "82 SUBSTITUTION ADV tak PUNCT \n",
- "83 SUBSTITUTION CCONJ i NOUN \n",
- "84 SUBSTITUTION NUM sto PUNCT \n",
- "85 CORRECT NUM sześćdziesiąt NUM \n",
- "86 CORRECT NUM dwa NUM \n",
- "87 DELETION ADV tam \n",
- "88 CORRECT VERB dojadÄ™ VERB \n",
- "89 SUBSTITUTION ADP do PUNCT \n",
- "90 SUBSTITUTION DET tej NOUN \n",
- "91 SUBSTITUTION NOUN ulicy PUNCT \n",
- "92 SUBSTITUTION ADV tak DET \n",
- "93 SUBSTITUTION VERB może PUNCT \n",
- "94 CORRECT NOUN pani NOUN \n",
- "95 INSERTION PUNCT \n",
- "96 CORRECT VERB wysiąść VERB \n",
- "97 SUBSTITUTION ADP na VERB \n",
- "98 SUBSTITUTION NOUN przystanku PRON \n",
- "99 SUBSTITUTION PROPN Bartycka NUM \n",
- "100 SUBSTITUTION CCONJ albo ADV \n",
- "101 SUBSTITUTION PROPN Sielce PUNCT \n",
- "102 SUBSTITUTION PROPN Bartycka X \n",
- "103 SUBSTITUTION CCONJ albo PUNCT \n",
- "104 CORRECT PUNCT ? PUNCT \n",
- "105 CORRECT PROPN Sielce PROPN \n",
- "106 SUBSTITUTION PROPN Sielce PUNCT \n",
- "107 SUBSTITUTION ADV tak PUNCT \n",
- "108 SUBSTITUTION PUNCT ? PROPN \n",
- "109 SUBSTITUTION ADV tak PUNCT \n",
- "110 SUBSTITUTION X aha PUNCT \n",
- "111 SUBSTITUTION CCONJ i PROPN \n",
- "112 SUBSTITUTION ADV tam PUNCT \n",
- "113 SUBSTITUTION ADP w PUNCT \n",
- "114 CORRECT NOUN pobliżu NOUN \n",
- "115 SUBSTITUTION AUX jest PUNCT \n",
- "116 SUBSTITUTION DET ta NOUN \n",
- "117 SUBSTITUTION NOUN ulica ADV \n",
- "118 CORRECT ADV tak ADV \n",
- "119 SUBSTITUTION PUNCT ? ADJ \n",
- "120 SUBSTITUTION CCONJ a PUNCT \n",
- "121 CORRECT NOUN Zwierzyniecka NOUN \n",
- "122 SUBSTITUTION ADJ wysoki PUNCT \n",
- "123 SUBSTITUTION NOUN numer NUM \n",
- "124 CORRECT VERB ma VERB \n",
- "125 DELETION NOUN pani \n",
- "126 SUBSTITUTION PUNCT ? PRON \n",
- "127 SUBSTITUTION PROPN Zwierzyniecka ADV \n",
- "128 CORRECT ADV zaraz ADV \n",
- "129 SUBSTITUTION NOUN momencik SCONJ \n",
- "130 SUBSTITUTION NUM osiem CCONJ \n",
- "131 SUBSTITUTION CCONJ A DET \n",
- "132 SUBSTITUTION PROPN Zwierzyniecka NOUN \n",
- "133 SUBSTITUTION AUX to VERB \n",
- "134 CORRECT PRON to PRON \n",
- "135 INSERTION ADJ \n",
- "136 SUBSTITUTION ADP przy ADV \n",
- "137 SUBSTITUTION PROPN Sielce VERB \n",
- "138 SUBSTITUTION NOUN trza CCONJ \n",
- "139 SUBSTITUTION VERB wysiąść NOUN \n",
- "140 SUBSTITUTION ADP przy ADJ \n",
- "141 SUBSTITUTION PROPN Sielce PUNCT \n",
- "142 SUBSTITUTION ADV tak NOUN \n",
- "143 CORRECT PUNCT ? PUNCT \n",
- "144 SUBSTITUTION ADV tak ADJ \n",
- "145 CORRECT NOUN przystanek NOUN \n",
- "146 SUBSTITUTION PROPN Sielce PUNCT \n",
- "147 SUBSTITUTION X aha NOUN \n",
- "148 SUBSTITUTION ADV tak PUNCT \n",
- "149 SUBSTITUTION PART no PUNCT \n",
- "150 SUBSTITUTION ADV dobrze PRON \n",
- "151 SUBSTITUTION CCONJ a PUNCT \n",
- "152 SUBSTITUTION PROPN Sielce ADP \n",
- "153 CORRECT PRON to PRON \n",
- "154 CORRECT VERB znaczy VERB \n",
- "155 DELETION DET jaka \n",
- "156 CORRECT AUX to AUX \n",
- "157 DELETION PART już \n",
- "158 SUBSTITUTION AUX jest NUM \n",
- "159 CORRECT NOUN dzielnica NOUN \n",
- "160 SUBSTITUTION AUX to ADJ \n",
- "161 SUBSTITUTION DET ta NOUN \n",
- "162 SUBSTITUTION AUX jest ADJ \n",
- "163 SUBSTITUTION ADP przy PUNCT \n",
- "164 CORRECT NOUN ulica NOUN \n",
- "165 DELETION PROPN Gagarina \n",
- "166 SUBSTITUTION CCONJ a PUNCT \n",
- "167 SUBSTITUTION ADP przy DET \n",
- "168 CORRECT NOUN ulicy NOUN \n",
- "169 SUBSTITUTION PROPN Gagarina PRON \n",
- "170 SUBSTITUTION CCONJ czyli ADV \n",
- "171 SUBSTITUTION PRON to PART \n",
- "172 SUBSTITUTION AUX jest DET \n",
- "173 CORRECT ADV tam ADV \n",
- "174 INSERTION NUM \n",
- "175 INSERTION CCONJ \n",
- "176 INSERTION NUM \n",
- "177 CORRECT NOUN Mokotów NOUN \n",
- "178 INSERTION PUNCT \n",
- "179 SUBSTITUTION ADP po NOUN \n",
- "180 SUBSTITUTION ADJ prostu PUNCT \n",
- "181 SUBSTITUTION ADV tak NOUN \n",
- "182 SUBSTITUTION PUNCT ? NOUN \n",
- "183 SUBSTITUTION ADV tak ADJ \n",
- "184 CORRECT NOUN Siekierki NOUN \n",
- "185 SUBSTITUTION PROPN Mokotów ADP \n",
- "186 SUBSTITUTION CCONJ a NOUN \n",
- "187 CORRECT NOUN Siekierki NOUN \n",
- "188 INSERTION PUNCT \n",
- "189 CORRECT PROPN Mokotów PROPN \n",
- "190 INSERTION PUNCT \n",
- "191 CORRECT CCONJ i CCONJ \n",
- "192 SUBSTITUTION ADV tam NOUN \n",
- "193 SUBSTITUTION SCONJ jak ADJ \n",
- "194 CORRECT NOUN pani NOUN \n",
- "195 CORRECT VERB wysiÄ…dzie VERB \n",
- "196 INSERTION ADP \n",
- "197 CORRECT DET to DET \n",
- "198 CORRECT NOUN trza NOUN \n",
- "199 SUBSTITUTION VERB wejść NOUN \n",
- "200 SUBSTITUTION ADP w PUNCT \n",
- "201 CORRECT NOUN lewo NOUN \n",
- "202 INSERTION PUNCT \n",
- "203 CORRECT ADP w ADP \n",
- "204 INSERTION PUNCT \n",
- "205 CORRECT NOUN ulicÄ™ NOUN \n",
- "206 SUBSTITUTION PROPN Nehru PUNCT \n",
- "207 SUBSTITUTION CCONJ i VERB \n",
- "208 SUBSTITUTION ADP od VERB \n",
- "209 SUBSTITUTION PROPN Nehru CCONJ \n",
- "210 SUBSTITUTION VERB odchodzi CCONJ \n",
- "211 SUBSTITUTION ADJ Zwierzyniecka PUNCT \n",
- "212 SUBSTITUTION ADP w PROPN \n",
- "213 SUBSTITUTION ADV lewo PUNCT \n",
- "214 CORRECT ADP w ADP \n",
- "215 DELETION ADV lewo \n",
- "216 SUBSTITUTION CCONJ i NOUN \n",
- "217 SUBSTITUTION NOUN ulica PUNCT \n",
- "218 SUBSTITUTION PROPN Nehru X \n",
- "219 CORRECT PUNCT ? PUNCT \n",
- "220 CORRECT ADV tak ADV \n",
- "221 DELETION PROPN Nehru \n",
- "222 SUBSTITUTION ADV dobrze NOUN \n",
- "223 CORRECT VERB dziękuję VERB \n",
- "224 CORRECT NOUN panu NOUN \n",
- "225 SUBSTITUTION ADV bardzo PUNCT \n",
- "226 SUBSTITUTION VERB proszÄ™ PROPN \n",
- "227 SUBSTITUTION ADP do PUNCT \n",
- "228 CORRECT NOUN widzenia NOUN \n",
- "229 SUBSTITUTION ADP do PUNCT \n",
- "230 CORRECT NOUN widzenia NOUN \n",
- "231 INSERTION PUNCT \n",
- "232 INSERTION SPACE \n",
- "\n",
- " hypothesis_word_text \n",
- "0 \n",
- "1 \n",
- "2 niedobre \n",
- "3 n \n",
- "4 . \n",
- "5 e \n",
- "6 . \n",
- "7 pracy \n",
- "8 a \n",
- "9 to \n",
- "10 \n",
- "11 długo \n",
- "12 nie \n",
- "13 było \n",
- "14 to \n",
- "15 dziecko \n",
- "16 czuje \n",
- "17 siÄ™ \n",
- "18 \n",
- "19 \n",
- "20 \n",
- "21 równie \n",
- "22 szybko \n",
- "23 jak \n",
- "24 to \n",
- "25 cecha \n",
- "26 brud \n",
- "27 ta \n",
- "28 na \n",
- "29 przykład \n",
- "30 siÄ™ \n",
- "31 ostatnio \n",
- "32 inżynierowie \n",
- "33 i \n",
- "34 brudno \n",
- "35 straszliwy \n",
- "36 szok \n",
- "37 brodatego \n",
- "38 ulica \n",
- "39 wyszogrodzka \n",
- "40 przy \n",
- "41 \n",
- "42 \n",
- "43 rembielińskiej \n",
- "44 ich \n",
- "45 cztero \n",
- "46 oto \n",
- "47 ta \n",
- "48 jak \n",
- "49 tak \n",
- "50 dużo \n",
- "51 punktów \n",
- "52 \n",
- "53 < \n",
- "54 \n",
- "55 \n",
- "56 \n",
- "57 \n",
- "58 unk \n",
- "59 \n",
- "60 > \n",
- "61 oni \n",
- "62 żeby \n",
- "63 podróży \n",
- "64 \n",
- "65 \n",
- "66 tramwajem \n",
- "67 do \n",
- "68 rondo \n",
- "69 Żaba \n",
- "70 \n",
- "71 < \n",
- "72 unk \n",
- "73 > \n",
- "74 toronto \n",
- "75 już \n",
- "76 sto \n",
- "77 sześćdziesiąt \n",
- "78 wojsk \n",
- "79 sto \n",
- "80 sześćdziesiąt \n",
- "81 ta \n",
- "82 < \n",
- "83 unk \n",
- "84 > \n",
- "85 trzysta \n",
- "86 sześćdziesiąt \n",
- "87 \n",
- "88 rataja \n",
- "89 < \n",
- "90 unk \n",
- "91 > \n",
- "92 tej \n",
- "93 < \n",
- "94 unk \n",
- "95 > \n",
- "96 może \n",
- "97 pojawić \n",
- "98 siÄ™ \n",
- "99 trzy \n",
- "100 stÄ…d \n",
- "101 < \n",
- "102 unk \n",
- "103 > \n",
- "104 < \n",
- "105 unk \n",
- "106 > \n",
- "107 < \n",
- "108 unk \n",
- "109 > \n",
- "110 < \n",
- "111 unk \n",
- "112 > \n",
- "113 < \n",
- "114 unk \n",
- "115 > \n",
- "116 berty \n",
- "117 coraz \n",
- "118 szybciej \n",
- "119 bartycka \n",
- "120 < \n",
- "121 unk \n",
- "122 > \n",
- "123 trzema \n",
- "124 trzeba \n",
- "125 \n",
- "126 siÄ™ \n",
- "127 trochÄ™ \n",
- "128 tak \n",
- "129 jak \n",
- "130 i \n",
- "131 te \n",
- "132 plany \n",
- "133 stały \n",
- "134 siÄ™ \n",
- "135 słynne \n",
- "136 ciężko \n",
- "137 dyszÄ…c \n",
- "138 i \n",
- "139 numer \n",
- "140 ewidencyjny \n",
- "141 < \n",
- "142 unk \n",
- "143 > \n",
- "144 nowy \n",
- "145 typ \n",
- "146 < \n",
- "147 unk \n",
- "148 > \n",
- "149 - \n",
- "150 siÄ™ \n",
- "151 - \n",
- "152 dla \n",
- "153 mnie \n",
- "154 trwało \n",
- "155 \n",
- "156 to \n",
- "157 \n",
- "158 trzy \n",
- "159 trzody \n",
- "160 ścięte \n",
- "161 tato \n",
- "162 taneczne \n",
- "163 < \n",
- "164 unk \n",
- "165 \n",
- "166 > \n",
- "167 ta \n",
- "168 notatka \n",
- "169 siÄ™ \n",
- "170 tutaj \n",
- "171 także \n",
- "172 kilka \n",
- "173 tutaj \n",
- "174 trzy \n",
- "175 czy \n",
- "176 cztery \n",
- "177 dni \n",
- "178 < \n",
- "179 unk \n",
- "180 > \n",
- "181 płyty \n",
- "182 darin \n",
- "183 nakryta \n",
- "184 plakatów \n",
- "185 pod \n",
- "186 hutach \n",
- "187 siekierkowskÄ… \n",
- "188 < \n",
- "189 unk \n",
- "190 > \n",
- "191 a \n",
- "192 siekierki \n",
- "193 hoszowski \n",
- "194 czytelnik \n",
- "195 wyszedł \n",
- "196 od \n",
- "197 swoich \n",
- "198 kolegów \n",
- "199 uliczek \n",
- "200 < \n",
- "201 unk \n",
- "202 > \n",
- "203 od \n",
- "204 < \n",
- "205 unk \n",
- "206 > \n",
- "207 odchodzi \n",
- "208 służy \n",
- "209 nie \n",
- "210 tylko \n",
- "211 < \n",
- "212 unk \n",
- "213 > \n",
- "214 na \n",
- "215 \n",
- "216 ulicach \n",
- "217 < \n",
- "218 unk \n",
- "219 > \n",
- "220 tak \n",
- "221 \n",
- "222 numeru \n",
- "223 krytykuje \n",
- "224 pan \n",
- "225 < \n",
- "226 unk \n",
- "227 > \n",
- "228 badania \n",
- "229 < \n",
- "230 unk \n",
- "231 > \n",
- "232 "
- ]
- },
- "metadata": {},
- "output_type": "display_data"
- },
- {
- "name": "stdout",
- "output_type": "stream",
- "text": [
- "\n"
- ]
- },
- {
- "data": {
- "text/html": [
- "<div>\n",
- "<style scoped>\n",
- " .dataframe tbody tr th:only-of-type {\n",
- " vertical-align: middle;\n",
- " }\n",
- "\n",
- " .dataframe tbody tr th {\n",
- " vertical-align: top;\n",
- " }\n",
- "\n",
- " .dataframe thead th {\n",
- " text-align: right;\n",
- " }\n",
- "</style>\n",
- "<table border=\"1\" class=\"dataframe\">\n",
- " <thead>\n",
- " <tr style=\"text-align: right;\">\n",
- " <th></th>\n",
- " <th>step_type</th>\n",
- " <th>reference_word_text</th>\n",
- " <th>hypothesis_word_text</th>\n",
- " </tr>\n",
- " </thead>\n",
- " <tbody>\n",
- " <tr>\n",
- " <th>0</th>\n",
- " <td>DELETION</td>\n",
- " <td>xxx</td>\n",
- " <td></td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>1</th>\n",
- " <td>DELETION</td>\n",
- " <td>dzień</td>\n",
- " <td></td>\n",
+ " <th>75</th>\n",
+ " <td>SUBSTITUTION</td>\n",
+ " <td>siÄ™</td>\n",
+ " <td><</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>2</th>\n",
- " <td>DELETION</td>\n",
- " <td>dobry</td>\n",
- " <td></td>\n",
+ " <th>76</th>\n",
+ " <td>SUBSTITUTION</td>\n",
+ " <td>zaczyna</td>\n",
+ " <td>unk</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>3</th>\n",
+ " <th>77</th>\n",
" <td>SUBSTITUTION</td>\n",
- " <td>dzień</td>\n",
- " <td>niedobre</td>\n",
+ " <td>Most</td>\n",
+ " <td>></td>\n",
" </tr>\n",
" <tr>\n",
- " <th>4</th>\n",
+ " <th>78</th>\n",
" <td>SUBSTITUTION</td>\n",
- " <td>dobry</td>\n",
- " <td>n</td>\n",
+ " <td>Siekierkowski</td>\n",
+ " <td>wielbłądy</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>5</th>\n",
+ " <th>79</th>\n",
" <td>SUBSTITUTION</td>\n",
- " <td>proszÄ™</td>\n",
- " <td>.</td>\n",
+ " <td>tam</td>\n",
+ " <td>siÄ™</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>6</th>\n",
+ " <th>80</th>\n",
" <td>SUBSTITUTION</td>\n",
- " <td>pana</td>\n",
- " <td>e</td>\n",
+ " <td>w</td>\n",
+ " <td>toczy</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>7</th>\n",
+ " <th>81</th>\n",
" <td>SUBSTITUTION</td>\n",
- " <td>ja</td>\n",
- " <td>.</td>\n",
+ " <td>stronÄ™</td>\n",
+ " <td>na</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>8</th>\n",
+ " <th>82</th>\n",
" <td>SUBSTITUTION</td>\n",
- " <td>chciałam</td>\n",
- " <td>pracy</td>\n",
+ " <td>Gocławia</td>\n",
+ " <td>most</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>9</th>\n",
+ " <th>83</th>\n",
" <td>SUBSTITUTION</td>\n",
- " <td>siÄ™</td>\n",
- " <td>a</td>\n",
+ " <td>gdzie</td>\n",
+ " <td>siekierkowski</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>10</th>\n",
+ " <th>84</th>\n",
" <td>SUBSTITUTION</td>\n",
- " <td>dowiedzieć</td>\n",
+ " <td>ma</td>\n",
" <td>to</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>11</th>\n",
+ " <th>85</th>\n",
" <td>SUBSTITUTION</td>\n",
- " <td>bo</td>\n",
- " <td>długo</td>\n",
+ " <td>on</td>\n",
+ " <td>trud</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>12</th>\n",
- " <td>CORRECT</td>\n",
- " <td>nie</td>\n",
- " <td>nie</td>\n",
+ " <th>86</th>\n",
+ " <td>SUBSTITUTION</td>\n",
+ " <td>przystanek</td>\n",
+ " <td>i</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>13</th>\n",
+ " <th>87</th>\n",
" <td>SUBSTITUTION</td>\n",
- " <td>bardzo</td>\n",
- " <td>było</td>\n",
+ " <td>pierwszy</td>\n",
+ " <td>czytanek</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>14</th>\n",
+ " <th>88</th>\n",
" <td>SUBSTITUTION</td>\n",
- " <td>wiem</td>\n",
- " <td>to</td>\n",
+ " <td>sto</td>\n",
+ " <td>pieszczoty</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>15</th>\n",
+ " <th>89</th>\n",
" <td>SUBSTITUTION</td>\n",
- " <td>gdzie</td>\n",
- " <td>dziecko</td>\n",
+ " <td>czterdzieści</td>\n",
+ " <td>siÄ™</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>16</th>\n",
+ " <th>90</th>\n",
+ " <td>CORRECT</td>\n",
+ " <td>trzy</td>\n",
+ " <td>trzy</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>91</th>\n",
" <td>SUBSTITUTION</td>\n",
- " <td>znajduje</td>\n",
- " <td>czuje</td>\n",
+ " <td>znaczy</td>\n",
+ " <td>płaczesz</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>17</th>\n",
+ " <th>92</th>\n",
" <td>CORRECT</td>\n",
- " <td>siÄ™</td>\n",
- " <td>siÄ™</td>\n",
+ " <td>tak</td>\n",
+ " <td>tak</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>18</th>\n",
- " <td>DELETION</td>\n",
- " <td>ulica</td>\n",
- " <td></td>\n",
+ " <th>93</th>\n",
+ " <td>CORRECT</td>\n",
+ " <td>naprawdÄ™</td>\n",
+ " <td>naprawdÄ™</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>19</th>\n",
+ " <th>94</th>\n",
" <td>SUBSTITUTION</td>\n",
- " <td>Zwierzyniecka</td>\n",
- " <td>równie</td>\n",
+ " <td>Most</td>\n",
+ " <td>może</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>20</th>\n",
+ " <th>95</th>\n",
" <td>SUBSTITUTION</td>\n",
- " <td>i</td>\n",
- " <td>szybko</td>\n",
+ " <td>Siekierkowski</td>\n",
+ " <td>kierkowski</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>21</th>\n",
+ " <th>96</th>\n",
" <td>CORRECT</td>\n",
- " <td>jak</td>\n",
- " <td>jak</td>\n",
+ " <td>to</td>\n",
+ " <td>to</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>22</th>\n",
+ " <th>97</th>\n",
" <td>DELETION</td>\n",
- " <td>dojechać</td>\n",
+ " <td>siÄ™</td>\n",
" <td></td>\n",
" </tr>\n",
" <tr>\n",
- " <th>23</th>\n",
+ " <th>98</th>\n",
" <td>DELETION</td>\n",
- " <td>z</td>\n",
+ " <td>zaczyna</td>\n",
" <td></td>\n",
" </tr>\n",
" <tr>\n",
- " <th>24</th>\n",
+ " <th>99</th>\n",
" <td>DELETION</td>\n",
- " <td>Bródna</td>\n",
+ " <td>za</td>\n",
" <td></td>\n",
" </tr>\n",
" <tr>\n",
- " <th>25</th>\n",
+ " <th>100</th>\n",
" <td>DELETION</td>\n",
- " <td>na</td>\n",
+ " <td>Siekierki</td>\n",
" <td></td>\n",
" </tr>\n",
" <tr>\n",
- " <th>26</th>\n",
+ " <th>101</th>\n",
" <td>SUBSTITUTION</td>\n",
- " <td>przykład</td>\n",
- " <td>to</td>\n",
+ " <td>Sanktuarium</td>\n",
+ " <td>zacznÄ…</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>27</th>\n",
+ " <th>102</th>\n",
" <td>SUBSTITUTION</td>\n",
- " <td>?</td>\n",
- " <td>cecha</td>\n",
+ " <td>no</td>\n",
+ " <td>siekierki</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>28</th>\n",
+ " <th>103</th>\n",
" <td>SUBSTITUTION</td>\n",
- " <td>na</td>\n",
- " <td>brud</td>\n",
+ " <td>właśnie</td>\n",
+ " <td>sanktuarium</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>29</th>\n",
+ " <th>104</th>\n",
" <td>SUBSTITUTION</td>\n",
- " <td>ZwierzynieckÄ…</td>\n",
- " <td>ta</td>\n",
+ " <td>przed</td>\n",
+ " <td>w</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>30</th>\n",
- " <td>CORRECT</td>\n",
- " <td>na</td>\n",
- " <td>na</td>\n",
+ " <th>105</th>\n",
+ " <td>SUBSTITUTION</td>\n",
+ " <td>tym</td>\n",
+ " <td>lourdes</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>31</th>\n",
- " <td>DELETION</td>\n",
- " <td>ZwierzynieckÄ…</td>\n",
- " <td></td>\n",
+ " <th>106</th>\n",
+ " <td>SUBSTITUTION</td>\n",
+ " <td>przed</td>\n",
+ " <td>siÄ™</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>32</th>\n",
+ " <th>107</th>\n",
+ " <td>CORRECT</td>\n",
+ " <td>tym</td>\n",
+ " <td>tym</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>108</th>\n",
" <td>DELETION</td>\n",
- " <td>a</td>\n",
+ " <td>przystanek</td>\n",
" <td></td>\n",
" </tr>\n",
" <tr>\n",
- " <th>33</th>\n",
+ " <th>109</th>\n",
" <td>DELETION</td>\n",
- " <td>z</td>\n",
+ " <td>o</td>\n",
" <td></td>\n",
" </tr>\n",
" <tr>\n",
- " <th>34</th>\n",
+ " <th>110</th>\n",
" <td>SUBSTITUTION</td>\n",
- " <td>Bródna</td>\n",
- " <td>przykład</td>\n",
+ " <td>której</td>\n",
+ " <td>przejęty</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>35</th>\n",
+ " <th>111</th>\n",
" <td>SUBSTITUTION</td>\n",
- " <td>z</td>\n",
- " <td>siÄ™</td>\n",
+ " <td>jest</td>\n",
+ " <td>przystanku</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>36</th>\n",
+ " <th>112</th>\n",
" <td>SUBSTITUTION</td>\n",
- " <td>którego</td>\n",
- " <td>ostatnio</td>\n",
+ " <td>sto</td>\n",
+ " <td>który</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>37</th>\n",
+ " <th>113</th>\n",
" <td>SUBSTITUTION</td>\n",
- " <td>miejsca</td>\n",
- " <td>inżynierowie</td>\n",
+ " <td>czterdzieści</td>\n",
+ " <td>torresie</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>38</th>\n",
+ " <th>114</th>\n",
" <td>SUBSTITUTION</td>\n",
- " <td>?</td>\n",
- " <td>i</td>\n",
+ " <td>trzy</td>\n",
+ " <td>czne</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>39</th>\n",
+ " <th>115</th>\n",
" <td>SUBSTITUTION</td>\n",
- " <td>z</td>\n",
- " <td>brudno</td>\n",
+ " <td>najbliższy</td>\n",
+ " <td>edition</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>40</th>\n",
+ " <th>116</th>\n",
" <td>SUBSTITUTION</td>\n",
- " <td>Bródna</td>\n",
- " <td>straszliwy</td>\n",
+ " <td>aha</td>\n",
+ " <td>-</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>41</th>\n",
- " <td>SUBSTITUTION</td>\n",
+ " <th>117</th>\n",
+ " <td>CORRECT</td>\n",
+ " <td>czyli</td>\n",
+ " <td>czyli</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>118</th>\n",
+ " <td>CORRECT</td>\n",
+ " <td>to</td>\n",
" <td>to</td>\n",
- " <td>szok</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>42</th>\n",
+ " <th>119</th>\n",
" <td>SUBSTITUTION</td>\n",
- " <td>jest</td>\n",
- " <td>brodatego</td>\n",
+ " <td>wtedy</td>\n",
+ " <td>wspólny</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>43</th>\n",
+ " <th>120</th>\n",
" <td>CORRECT</td>\n",
- " <td>ulica</td>\n",
- " <td>ulica</td>\n",
+ " <td>przystanek</td>\n",
+ " <td>przystanek</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>44</th>\n",
- " <td>DELETION</td>\n",
- " <td>Wyszogrodzka</td>\n",
- " <td></td>\n",
+ " <th>121</th>\n",
+ " <td>SUBSTITUTION</td>\n",
+ " <td>Małe</td>\n",
+ " <td>małe</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>45</th>\n",
+ " <th>122</th>\n",
" <td>SUBSTITUTION</td>\n",
- " <td>tu</td>\n",
- " <td>wyszogrodzka</td>\n",
+ " <td>Siekierki</td>\n",
+ " <td>siekierki</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>46</th>\n",
+ " <th>123</th>\n",
" <td>CORRECT</td>\n",
- " <td>przy</td>\n",
- " <td>przy</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>47</th>\n",
- " <td>DELETION</td>\n",
- " <td>Rembielińskiej</td>\n",
- " <td></td>\n",
+ " <td>ale</td>\n",
+ " <td>ale</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>48</th>\n",
- " <td>DELETION</td>\n",
- " <td>czyli</td>\n",
- " <td></td>\n",
+ " <th>124</th>\n",
+ " <td>CORRECT</td>\n",
+ " <td>to</td>\n",
+ " <td>to</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>49</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>przy</td>\n",
- " <td>rembielińskiej</td>\n",
+ " <th>125</th>\n",
+ " <td>CORRECT</td>\n",
+ " <td>nie</td>\n",
+ " <td>nie</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>50</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>tramwajach</td>\n",
- " <td>ich</td>\n",
+ " <th>126</th>\n",
+ " <td>DELETION</td>\n",
+ " <td>jest</td>\n",
+ " <td></td>\n",
" </tr>\n",
" <tr>\n",
- " <th>51</th>\n",
- " <td>SUBSTITUTION</td>\n",
+ " <th>127</th>\n",
+ " <td>DELETION</td>\n",
" <td>tak</td>\n",
- " <td>cztero</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>52</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>?</td>\n",
- " <td>oto</td>\n",
+ " <td></td>\n",
" </tr>\n",
" <tr>\n",
- " <th>53</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>przy</td>\n",
- " <td>ta</td>\n",
+ " <th>128</th>\n",
+ " <td>DELETION</td>\n",
+ " <td>tak</td>\n",
+ " <td></td>\n",
" </tr>\n",
" <tr>\n",
- " <th>54</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>tramwajach</td>\n",
- " <td>jak</td>\n",
+ " <th>129</th>\n",
+ " <td>DELETION</td>\n",
+ " <td>tak</td>\n",
+ " <td></td>\n",
" </tr>\n",
" <tr>\n",
- " <th>55</th>\n",
- " <td>CORRECT</td>\n",
- " <td>tak</td>\n",
+ " <th>130</th>\n",
+ " <td>DELETION</td>\n",
" <td>tak</td>\n",
+ " <td></td>\n",
" </tr>\n",
" <tr>\n",
- " <th>56</th>\n",
+ " <th>131</th>\n",
" <td>DELETION</td>\n",
- " <td>może</td>\n",
+ " <td>na</td>\n",
" <td></td>\n",
" </tr>\n",
" <tr>\n",
- " <th>57</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>pani</td>\n",
- " <td>dużo</td>\n",
+ " <th>132</th>\n",
+ " <td>DELETION</td>\n",
+ " <td>wysokości</td>\n",
+ " <td></td>\n",
" </tr>\n",
" <tr>\n",
- " <th>58</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>poczeka</td>\n",
- " <td>punktów</td>\n",
+ " <th>133</th>\n",
+ " <td>DELETION</td>\n",
+ " <td>Panoramy</td>\n",
+ " <td></td>\n",
" </tr>\n",
" <tr>\n",
- " <th>59</th>\n",
+ " <th>134</th>\n",
" <td>SUBSTITUTION</td>\n",
- " <td>sprawdzÄ™</td>\n",
- " <td><</td>\n",
+ " <td>aha</td>\n",
+ " <td>do</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>60</th>\n",
+ " <th>135</th>\n",
" <td>SUBSTITUTION</td>\n",
" <td>dobrze</td>\n",
- " <td>unk</td>\n",
+ " <td>końca</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>61</th>\n",
+ " <th>136</th>\n",
" <td>SUBSTITUTION</td>\n",
- " <td>dobrze</td>\n",
- " <td>></td>\n",
+ " <td>najbliższy</td>\n",
+ " <td>dotrzymać</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>62</th>\n",
+ " <th>137</th>\n",
" <td>SUBSTITUTION</td>\n",
- " <td>pani</td>\n",
- " <td>oni</td>\n",
+ " <td>już</td>\n",
+ " <td>dziÅ›</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>63</th>\n",
+ " <th>138</th>\n",
" <td>SUBSTITUTION</td>\n",
- " <td>sobie</td>\n",
- " <td>żeby</td>\n",
+ " <td>chwileczkÄ™</td>\n",
+ " <td>sÄ…</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>64</th>\n",
+ " <th>139</th>\n",
" <td>SUBSTITUTION</td>\n",
- " <td>podjedzie</td>\n",
- " <td>podróży</td>\n",
+ " <td>czternasta</td>\n",
+ " <td>czternastej</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>65</th>\n",
+ " <th>140</th>\n",
" <td>CORRECT</td>\n",
- " <td>tramwajem</td>\n",
- " <td>tramwajem</td>\n",
+ " <td>czterdzieści</td>\n",
+ " <td>czterdzieści</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>66</th>\n",
+ " <th>141</th>\n",
" <td>CORRECT</td>\n",
- " <td>do</td>\n",
- " <td>do</td>\n",
+ " <td>sześć</td>\n",
+ " <td>sześć</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>67</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>Ronda</td>\n",
- " <td>rondo</td>\n",
+ " <th>142</th>\n",
+ " <td>DELETION</td>\n",
+ " <td>piętnasta</td>\n",
+ " <td></td>\n",
" </tr>\n",
" <tr>\n",
- " <th>68</th>\n",
- " <td>CORRECT</td>\n",
- " <td>Żaba</td>\n",
- " <td>Żaba</td>\n",
+ " <th>143</th>\n",
+ " <td>DELETION</td>\n",
+ " <td>zero</td>\n",
+ " <td></td>\n",
" </tr>\n",
" <tr>\n",
- " <th>69</th>\n",
+ " <th>144</th>\n",
+ " <td>DELETION</td>\n",
+ " <td>jeden</td>\n",
+ " <td></td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>145</th>\n",
+ " <td>DELETION</td>\n",
+ " <td>aha</td>\n",
+ " <td></td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>146</th>\n",
" <td>SUBSTITUTION</td>\n",
- " <td>tak</td>\n",
- " <td><</td>\n",
+ " <td>no</td>\n",
+ " <td>piętnasto</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>70</th>\n",
+ " <th>147</th>\n",
" <td>SUBSTITUTION</td>\n",
- " <td>od</td>\n",
- " <td>unk</td>\n",
+ " <td>dobrze</td>\n",
+ " <td>żeruje</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>71</th>\n",
+ " <th>148</th>\n",
" <td>SUBSTITUTION</td>\n",
- " <td>Ronda</td>\n",
- " <td>></td>\n",
+ " <td>dziękuję</td>\n",
+ " <td>a</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>72</th>\n",
+ " <th>149</th>\n",
" <td>SUBSTITUTION</td>\n",
- " <td>Żaba</td>\n",
- " <td>toronto</td>\n",
+ " <td>do</td>\n",
+ " <td>nowy</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>73</th>\n",
- " <td>CORRECT</td>\n",
- " <td>już</td>\n",
- " <td>już</td>\n",
+ " <th>150</th>\n",
+ " <td>SUBSTITUTION</td>\n",
+ " <td>widzenia</td>\n",
+ " <td>gen</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>74</th>\n",
- " <td>CORRECT</td>\n",
- " <td>sto</td>\n",
- " <td>sto</td>\n",
+ " <th>151</th>\n",
+ " <td>SUBSTITUTION</td>\n",
+ " <td>do</td>\n",
+ " <td>.</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>75</th>\n",
- " <td>CORRECT</td>\n",
- " <td>sześćdziesiąt</td>\n",
- " <td>sześćdziesiąt</td>\n",
+ " <th>152</th>\n",
+ " <td>SUBSTITUTION</td>\n",
+ " <td>widzenia</td>\n",
+ " <td></td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ " step_type reference_word_text hypothesis_word_text\n",
+ "0 DELETION xxx \n",
+ "1 DELETION dzień \n",
+ "2 DELETION dobry \n",
+ "3 SUBSTITUTION dzień dobre\n",
+ "4 SUBSTITUTION dobry dyrektor\n",
+ "5 CORRECT proszÄ™ proszÄ™\n",
+ "6 DELETION pana \n",
+ "7 DELETION ja \n",
+ "8 SUBSTITUTION mam wybaczyć\n",
+ "9 SUBSTITUTION o tryb\n",
+ "10 SUBSTITUTION której numer\n",
+ "11 SUBSTITUTION będzie jeden\n",
+ "12 SUBSTITUTION sto to\n",
+ "13 SUBSTITUTION czterdzieści teresie\n",
+ "14 SUBSTITUTION trzy trzeba\n",
+ "15 CORRECT będzie będzie\n",
+ "16 CORRECT najbliższy najbliższy\n",
+ "17 SUBSTITUTION z ale\n",
+ "18 SUBSTITUTION Alei i\n",
+ "19 SUBSTITUTION Alei tu\n",
+ "20 SUBSTITUTION Witosa aleje\n",
+ "21 SUBSTITUTION w pić\n",
+ "22 SUBSTITUTION stronÄ™ od\n",
+ "23 SUBSTITUTION Gocławia roztropnego\n",
+ "24 SUBSTITUTION z działania\n",
+ "25 SUBSTITUTION tego swego\n",
+ "26 SUBSTITUTION przystanku przystankom\n",
+ "27 CORRECT vis vis\n",
+ "28 CORRECT - -\n",
+ "29 CORRECT a a\n",
+ "30 CORRECT - -\n",
+ "31 CORRECT vis vis\n",
+ "32 INSERTION zus\n",
+ "33 INSERTION -\n",
+ "34 SUBSTITUTION ZUSu u\n",
+ "35 SUBSTITUTION tak to\n",
+ "36 SUBSTITUTION ? jak\n",
+ "37 SUBSTITUTION no mnie\n",
+ "38 CORRECT nie nie\n",
+ "39 SUBSTITUTION nie <\n",
+ "40 SUBSTITUTION tam unk\n",
+ "41 SUBSTITUTION vis >\n",
+ "42 SUBSTITUTION - widać\n",
+ "43 SUBSTITUTION a <\n",
+ "44 SUBSTITUTION - unk\n",
+ "45 SUBSTITUTION vis >\n",
+ "46 SUBSTITUTION Panoramy panoramÄ™\n",
+ "47 CORRECT przez przez\n",
+ "48 SUBSTITUTION Siekierkowski siekierko\n",
+ "49 SUBSTITUTION tam trwałego\n",
+ "50 SUBSTITUTION w tonÄ™\n",
+ "51 SUBSTITUTION stronÄ™ antoniego\n",
+ "52 SUBSTITUTION Gocławia przystanki\n",
+ "53 SUBSTITUTION ale kolejowe\n",
+ "54 CORRECT to to\n",
+ "55 DELETION nie \n",
+ "56 DELETION z \n",
+ "57 DELETION tego \n",
+ "58 DELETION przystanku \n",
+ "59 DELETION Aleja \n",
+ "60 DELETION Witosa \n",
+ "61 DELETION ? \n",
+ "62 DELETION no \n",
+ "63 SUBSTITUTION to było\n",
+ "64 SUBSTITUTION jest coÅ›\n",
+ "65 CORRECT czy czy\n",
+ "66 SUBSTITUTION Bartoszka bartoszka\n",
+ "67 CORRECT na na\n",
+ "68 CORRECT żądanie żądanie\n",
+ "69 INSERTION <\n",
+ "70 INSERTION unk\n",
+ "71 SUBSTITUTION wie >\n",
+ "72 SUBSTITUTION pan <\n",
+ "73 SUBSTITUTION gdzie unk\n",
+ "74 SUBSTITUTION jest >\n",
+ "75 SUBSTITUTION siÄ™ <\n",
+ "76 SUBSTITUTION zaczyna unk\n",
+ "77 SUBSTITUTION Most >\n",
+ "78 SUBSTITUTION Siekierkowski wielbłądy\n",
+ "79 SUBSTITUTION tam siÄ™\n",
+ "80 SUBSTITUTION w toczy\n",
+ "81 SUBSTITUTION stronÄ™ na\n",
+ "82 SUBSTITUTION Gocławia most\n",
+ "83 SUBSTITUTION gdzie siekierkowski\n",
+ "84 SUBSTITUTION ma to\n",
+ "85 SUBSTITUTION on trud\n",
+ "86 SUBSTITUTION przystanek i\n",
+ "87 SUBSTITUTION pierwszy czytanek\n",
+ "88 SUBSTITUTION sto pieszczoty\n",
+ "89 SUBSTITUTION czterdzieści się\n",
+ "90 CORRECT trzy trzy\n",
+ "91 SUBSTITUTION znaczy płaczesz\n",
+ "92 CORRECT tak tak\n",
+ "93 CORRECT naprawdÄ™ naprawdÄ™\n",
+ "94 SUBSTITUTION Most może\n",
+ "95 SUBSTITUTION Siekierkowski kierkowski\n",
+ "96 CORRECT to to\n",
+ "97 DELETION siÄ™ \n",
+ "98 DELETION zaczyna \n",
+ "99 DELETION za \n",
+ "100 DELETION Siekierki \n",
+ "101 SUBSTITUTION Sanktuarium zacznÄ…\n",
+ "102 SUBSTITUTION no siekierki\n",
+ "103 SUBSTITUTION właśnie sanktuarium\n",
+ "104 SUBSTITUTION przed w\n",
+ "105 SUBSTITUTION tym lourdes\n",
+ "106 SUBSTITUTION przed siÄ™\n",
+ "107 CORRECT tym tym\n",
+ "108 DELETION przystanek \n",
+ "109 DELETION o \n",
+ "110 SUBSTITUTION której przejęty\n",
+ "111 SUBSTITUTION jest przystanku\n",
+ "112 SUBSTITUTION sto który\n",
+ "113 SUBSTITUTION czterdzieści torresie\n",
+ "114 SUBSTITUTION trzy czne\n",
+ "115 SUBSTITUTION najbliższy edition\n",
+ "116 SUBSTITUTION aha -\n",
+ "117 CORRECT czyli czyli\n",
+ "118 CORRECT to to\n",
+ "119 SUBSTITUTION wtedy wspólny\n",
+ "120 CORRECT przystanek przystanek\n",
+ "121 SUBSTITUTION Małe małe\n",
+ "122 SUBSTITUTION Siekierki siekierki\n",
+ "123 CORRECT ale ale\n",
+ "124 CORRECT to to\n",
+ "125 CORRECT nie nie\n",
+ "126 DELETION jest \n",
+ "127 DELETION tak \n",
+ "128 DELETION tak \n",
+ "129 DELETION tak \n",
+ "130 DELETION tak \n",
+ "131 DELETION na \n",
+ "132 DELETION wysokości \n",
+ "133 DELETION Panoramy \n",
+ "134 SUBSTITUTION aha do\n",
+ "135 SUBSTITUTION dobrze końca\n",
+ "136 SUBSTITUTION najbliższy dotrzymać\n",
+ "137 SUBSTITUTION już dziś\n",
+ "138 SUBSTITUTION chwileczkÄ™ sÄ…\n",
+ "139 SUBSTITUTION czternasta czternastej\n",
+ "140 CORRECT czterdzieści czterdzieści\n",
+ "141 CORRECT sześć sześć\n",
+ "142 DELETION piętnasta \n",
+ "143 DELETION zero \n",
+ "144 DELETION jeden \n",
+ "145 DELETION aha \n",
+ "146 SUBSTITUTION no piętnasto\n",
+ "147 SUBSTITUTION dobrze żeruje\n",
+ "148 SUBSTITUTION dziękuję a\n",
+ "149 SUBSTITUTION do nowy\n",
+ "150 SUBSTITUTION widzenia gen\n",
+ "151 SUBSTITUTION do .\n",
+ "152 SUBSTITUTION widzenia "
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "\n"
+ ]
+ },
+ {
+ "data": {
+ "text/html": [
+ "<div>\n",
+ "<style scoped>\n",
+ " .dataframe tbody tr th:only-of-type {\n",
+ " vertical-align: middle;\n",
+ " }\n",
+ "\n",
+ " .dataframe tbody tr th {\n",
+ " vertical-align: top;\n",
+ " }\n",
+ "\n",
+ " .dataframe thead th {\n",
+ " text-align: right;\n",
+ " }\n",
+ "</style>\n",
+ "<table border=\"1\" class=\"dataframe\">\n",
+ " <thead>\n",
+ " <tr style=\"text-align: right;\">\n",
+ " <th></th>\n",
+ " <th>step_type</th>\n",
+ " <th>reference_word_text</th>\n",
+ " <th>hypothesis_word_text</th>\n",
" </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
" <tr>\n",
- " <th>76</th>\n",
+ " <th>0</th>\n",
" <td>DELETION</td>\n",
- " <td>dwa</td>\n",
+ " <td>_</td>\n",
" <td></td>\n",
" </tr>\n",
" <tr>\n",
- " <th>77</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>jest</td>\n",
- " <td>wojsk</td>\n",
+ " <th>1</th>\n",
+ " <td>DELETION</td>\n",
+ " <td>_</td>\n",
+ " <td></td>\n",
" </tr>\n",
" <tr>\n",
- " <th>78</th>\n",
- " <td>CORRECT</td>\n",
- " <td>sto</td>\n",
- " <td>sto</td>\n",
+ " <th>2</th>\n",
+ " <td>DELETION</td>\n",
+ " <td>_</td>\n",
+ " <td></td>\n",
" </tr>\n",
" <tr>\n",
- " <th>79</th>\n",
- " <td>CORRECT</td>\n",
- " <td>sześćdziesiąt</td>\n",
- " <td>sześćdziesiąt</td>\n",
+ " <th>3</th>\n",
+ " <td>DELETION</td>\n",
+ " <td>_</td>\n",
+ " <td></td>\n",
" </tr>\n",
" <tr>\n",
- " <th>80</th>\n",
- " <td>INSERTION</td>\n",
+ " <th>4</th>\n",
+ " <td>DELETION</td>\n",
+ " <td>_</td>\n",
" <td></td>\n",
- " <td>ta</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>81</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>dwa</td>\n",
- " <td><</td>\n",
+ " <th>5</th>\n",
+ " <td>CORRECT</td>\n",
+ " <td>_</td>\n",
+ " <td>_</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>82</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>tak</td>\n",
- " <td>unk</td>\n",
+ " <th>6</th>\n",
+ " <td>CORRECT</td>\n",
+ " <td>_</td>\n",
+ " <td>_</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>83</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>i</td>\n",
- " <td>></td>\n",
+ " <th>7</th>\n",
+ " <td>CORRECT</td>\n",
+ " <td>_</td>\n",
+ " <td>_</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>84</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>sto</td>\n",
- " <td>trzysta</td>\n",
+ " <th>8</th>\n",
+ " <td>CORRECT</td>\n",
+ " <td>_</td>\n",
+ " <td>_</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>85</th>\n",
+ " <th>9</th>\n",
" <td>CORRECT</td>\n",
- " <td>sześćdziesiąt</td>\n",
- " <td>sześćdziesiąt</td>\n",
+ " <td>_</td>\n",
+ " <td>_</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>86</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>dwa</td>\n",
- " <td>rataja</td>\n",
+ " <th>10</th>\n",
+ " <td>CORRECT</td>\n",
+ " <td>_</td>\n",
+ " <td>_</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>87</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>tam</td>\n",
- " <td><</td>\n",
+ " <th>11</th>\n",
+ " <td>CORRECT</td>\n",
+ " <td>_</td>\n",
+ " <td>_</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>88</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>dojadÄ™</td>\n",
- " <td>unk</td>\n",
+ " <th>12</th>\n",
+ " <td>CORRECT</td>\n",
+ " <td>_</td>\n",
+ " <td>_</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>89</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>do</td>\n",
- " <td>></td>\n",
+ " <th>13</th>\n",
+ " <td>CORRECT</td>\n",
+ " <td>_</td>\n",
+ " <td>_</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>90</th>\n",
+ " <th>14</th>\n",
" <td>CORRECT</td>\n",
- " <td>tej</td>\n",
- " <td>tej</td>\n",
+ " <td>_</td>\n",
+ " <td>_</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>91</th>\n",
- " <td>INSERTION</td>\n",
- " <td></td>\n",
- " <td><</td>\n",
+ " <th>15</th>\n",
+ " <td>CORRECT</td>\n",
+ " <td>_</td>\n",
+ " <td>_</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>92</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>ulicy</td>\n",
- " <td>unk</td>\n",
+ " <th>16</th>\n",
+ " <td>CORRECT</td>\n",
+ " <td>_</td>\n",
+ " <td>_</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>93</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>tak</td>\n",
- " <td>></td>\n",
+ " <th>17</th>\n",
+ " <td>CORRECT</td>\n",
+ " <td>_</td>\n",
+ " <td>_</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>94</th>\n",
- " <td>CORRECT</td>\n",
- " <td>może</td>\n",
- " <td>może</td>\n",
+ " <th>18</th>\n",
+ " <td>DELETION</td>\n",
+ " <td>geogName</td>\n",
+ " <td></td>\n",
" </tr>\n",
" <tr>\n",
- " <th>95</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>pani</td>\n",
- " <td>pojawić</td>\n",
+ " <th>19</th>\n",
+ " <td>DELETION</td>\n",
+ " <td>geogName</td>\n",
+ " <td></td>\n",
" </tr>\n",
" <tr>\n",
- " <th>96</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>wysiąść</td>\n",
- " <td>siÄ™</td>\n",
+ " <th>20</th>\n",
+ " <td>DELETION</td>\n",
+ " <td>geogName</td>\n",
+ " <td></td>\n",
" </tr>\n",
" <tr>\n",
- " <th>97</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>na</td>\n",
- " <td>trzy</td>\n",
+ " <th>21</th>\n",
+ " <td>CORRECT</td>\n",
+ " <td>_</td>\n",
+ " <td>_</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>98</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>przystanku</td>\n",
- " <td>stÄ…d</td>\n",
+ " <th>22</th>\n",
+ " <td>CORRECT</td>\n",
+ " <td>_</td>\n",
+ " <td>_</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>99</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>Bartycka</td>\n",
- " <td><</td>\n",
+ " <th>23</th>\n",
+ " <td>DELETION</td>\n",
+ " <td>placeName</td>\n",
+ " <td></td>\n",
" </tr>\n",
" <tr>\n",
- " <th>100</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>albo</td>\n",
- " <td>unk</td>\n",
+ " <th>24</th>\n",
+ " <td>CORRECT</td>\n",
+ " <td>_</td>\n",
+ " <td>_</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>101</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>Sielce</td>\n",
- " <td>></td>\n",
+ " <th>25</th>\n",
+ " <td>CORRECT</td>\n",
+ " <td>_</td>\n",
+ " <td>_</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>102</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>Bartycka</td>\n",
- " <td><</td>\n",
+ " <th>26</th>\n",
+ " <td>CORRECT</td>\n",
+ " <td>_</td>\n",
+ " <td>_</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>103</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>albo</td>\n",
- " <td>unk</td>\n",
+ " <th>27</th>\n",
+ " <td>CORRECT</td>\n",
+ " <td>_</td>\n",
+ " <td>_</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>104</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>?</td>\n",
- " <td>></td>\n",
+ " <th>28</th>\n",
+ " <td>CORRECT</td>\n",
+ " <td>_</td>\n",
+ " <td>_</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>105</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>Sielce</td>\n",
- " <td><</td>\n",
+ " <th>29</th>\n",
+ " <td>CORRECT</td>\n",
+ " <td>_</td>\n",
+ " <td>_</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>106</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>Sielce</td>\n",
- " <td>unk</td>\n",
+ " <th>30</th>\n",
+ " <td>CORRECT</td>\n",
+ " <td>_</td>\n",
+ " <td>_</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>107</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>tak</td>\n",
- " <td>></td>\n",
+ " <th>31</th>\n",
+ " <td>CORRECT</td>\n",
+ " <td>_</td>\n",
+ " <td>_</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>108</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>?</td>\n",
- " <td><</td>\n",
+ " <th>32</th>\n",
+ " <td>DELETION</td>\n",
+ " <td>orgName</td>\n",
+ " <td></td>\n",
" </tr>\n",
" <tr>\n",
- " <th>109</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>tak</td>\n",
- " <td>unk</td>\n",
+ " <th>33</th>\n",
+ " <td>CORRECT</td>\n",
+ " <td>_</td>\n",
+ " <td>_</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>110</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>aha</td>\n",
- " <td>></td>\n",
+ " <th>34</th>\n",
+ " <td>CORRECT</td>\n",
+ " <td>_</td>\n",
+ " <td>_</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>111</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>i</td>\n",
- " <td><</td>\n",
+ " <th>35</th>\n",
+ " <td>CORRECT</td>\n",
+ " <td>_</td>\n",
+ " <td>_</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>112</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>tam</td>\n",
- " <td>unk</td>\n",
+ " <th>36</th>\n",
+ " <td>CORRECT</td>\n",
+ " <td>_</td>\n",
+ " <td>_</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>113</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>w</td>\n",
- " <td>></td>\n",
+ " <th>37</th>\n",
+ " <td>CORRECT</td>\n",
+ " <td>_</td>\n",
+ " <td>_</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>114</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>pobliżu</td>\n",
- " <td>berty</td>\n",
+ " <th>38</th>\n",
+ " <td>CORRECT</td>\n",
+ " <td>_</td>\n",
+ " <td>_</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>115</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>jest</td>\n",
- " <td>coraz</td>\n",
+ " <th>39</th>\n",
+ " <td>CORRECT</td>\n",
+ " <td>_</td>\n",
+ " <td>_</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>116</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>ta</td>\n",
- " <td>szybciej</td>\n",
+ " <th>40</th>\n",
+ " <td>CORRECT</td>\n",
+ " <td>_</td>\n",
+ " <td>_</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>117</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>ulica</td>\n",
- " <td>bartycka</td>\n",
+ " <th>41</th>\n",
+ " <td>CORRECT</td>\n",
+ " <td>_</td>\n",
+ " <td>_</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>118</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>tak</td>\n",
- " <td><</td>\n",
+ " <th>42</th>\n",
+ " <td>CORRECT</td>\n",
+ " <td>_</td>\n",
+ " <td>_</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>119</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>?</td>\n",
- " <td>unk</td>\n",
+ " <th>43</th>\n",
+ " <td>DELETION</td>\n",
+ " <td>geogName</td>\n",
+ " <td></td>\n",
" </tr>\n",
" <tr>\n",
- " <th>120</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>a</td>\n",
- " <td>></td>\n",
+ " <th>44</th>\n",
+ " <td>DELETION</td>\n",
+ " <td>geogName</td>\n",
+ " <td></td>\n",
" </tr>\n",
" <tr>\n",
- " <th>121</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>Zwierzyniecka</td>\n",
- " <td>trzema</td>\n",
+ " <th>45</th>\n",
+ " <td>CORRECT</td>\n",
+ " <td>_</td>\n",
+ " <td>_</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>122</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>wysoki</td>\n",
- " <td>trzeba</td>\n",
+ " <th>46</th>\n",
+ " <td>CORRECT</td>\n",
+ " <td>placeName</td>\n",
+ " <td>placeName</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>123</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>numer</td>\n",
- " <td>siÄ™</td>\n",
+ " <th>47</th>\n",
+ " <td>CORRECT</td>\n",
+ " <td>_</td>\n",
+ " <td>_</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>124</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>ma</td>\n",
- " <td>trochÄ™</td>\n",
+ " <th>48</th>\n",
+ " <td>CORRECT</td>\n",
+ " <td>_</td>\n",
+ " <td>_</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>125</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>pani</td>\n",
- " <td>tak</td>\n",
+ " <th>49</th>\n",
+ " <td>CORRECT</td>\n",
+ " <td>_</td>\n",
+ " <td>_</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>126</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>?</td>\n",
- " <td>jak</td>\n",
+ " <th>50</th>\n",
+ " <td>DELETION</td>\n",
+ " <td>placeName</td>\n",
+ " <td></td>\n",
" </tr>\n",
" <tr>\n",
- " <th>127</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>Zwierzyniecka</td>\n",
- " <td>i</td>\n",
+ " <th>51</th>\n",
+ " <td>CORRECT</td>\n",
+ " <td>_</td>\n",
+ " <td>_</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>128</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>zaraz</td>\n",
- " <td>te</td>\n",
+ " <th>52</th>\n",
+ " <td>CORRECT</td>\n",
+ " <td>_</td>\n",
+ " <td>_</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>129</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>momencik</td>\n",
- " <td>plany</td>\n",
+ " <th>53</th>\n",
+ " <td>CORRECT</td>\n",
+ " <td>_</td>\n",
+ " <td>_</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>130</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>osiem</td>\n",
- " <td>stały</td>\n",
+ " <th>54</th>\n",
+ " <td>CORRECT</td>\n",
+ " <td>_</td>\n",
+ " <td>_</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>131</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>A</td>\n",
- " <td>siÄ™</td>\n",
+ " <th>55</th>\n",
+ " <td>CORRECT</td>\n",
+ " <td>_</td>\n",
+ " <td>_</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>132</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>Zwierzyniecka</td>\n",
- " <td>słynne</td>\n",
+ " <th>56</th>\n",
+ " <td>CORRECT</td>\n",
+ " <td>_</td>\n",
+ " <td>_</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>133</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>to</td>\n",
- " <td>ciężko</td>\n",
+ " <th>57</th>\n",
+ " <td>DELETION</td>\n",
+ " <td>geogName</td>\n",
+ " <td></td>\n",
" </tr>\n",
" <tr>\n",
- " <th>134</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>to</td>\n",
- " <td>dyszÄ…c</td>\n",
+ " <th>58</th>\n",
+ " <td>CORRECT</td>\n",
+ " <td>_</td>\n",
+ " <td>_</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>135</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>przy</td>\n",
- " <td>i</td>\n",
+ " <th>59</th>\n",
+ " <td>CORRECT</td>\n",
+ " <td>_</td>\n",
+ " <td>_</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>136</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>Sielce</td>\n",
- " <td>numer</td>\n",
+ " <th>60</th>\n",
+ " <td>CORRECT</td>\n",
+ " <td>_</td>\n",
+ " <td>_</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>137</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>trza</td>\n",
- " <td>ewidencyjny</td>\n",
+ " <th>61</th>\n",
+ " <td>CORRECT</td>\n",
+ " <td>_</td>\n",
+ " <td>_</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>138</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>wysiąść</td>\n",
- " <td><</td>\n",
+ " <th>62</th>\n",
+ " <td>CORRECT</td>\n",
+ " <td>_</td>\n",
+ " <td>_</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>139</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>przy</td>\n",
- " <td>unk</td>\n",
+ " <th>63</th>\n",
+ " <td>CORRECT</td>\n",
+ " <td>_</td>\n",
+ " <td>_</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>140</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>Sielce</td>\n",
- " <td>></td>\n",
+ " <th>64</th>\n",
+ " <td>DELETION</td>\n",
+ " <td>persName</td>\n",
+ " <td></td>\n",
" </tr>\n",
" <tr>\n",
- " <th>141</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>tak</td>\n",
- " <td>nowy</td>\n",
+ " <th>65</th>\n",
+ " <td>CORRECT</td>\n",
+ " <td>_</td>\n",
+ " <td>_</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>142</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>?</td>\n",
- " <td>typ</td>\n",
+ " <th>66</th>\n",
+ " <td>CORRECT</td>\n",
+ " <td>_</td>\n",
+ " <td>_</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>143</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>tak</td>\n",
- " <td><</td>\n",
+ " <th>67</th>\n",
+ " <td>CORRECT</td>\n",
+ " <td>_</td>\n",
+ " <td>_</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>144</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>przystanek</td>\n",
- " <td>unk</td>\n",
+ " <th>68</th>\n",
+ " <td>CORRECT</td>\n",
+ " <td>_</td>\n",
+ " <td>_</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>69</th>\n",
+ " <td>CORRECT</td>\n",
+ " <td>_</td>\n",
+ " <td>_</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>145</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>Sielce</td>\n",
- " <td>></td>\n",
+ " <th>70</th>\n",
+ " <td>CORRECT</td>\n",
+ " <td>_</td>\n",
+ " <td>_</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>146</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>aha</td>\n",
- " <td>-</td>\n",
+ " <th>71</th>\n",
+ " <td>CORRECT</td>\n",
+ " <td>_</td>\n",
+ " <td>_</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>147</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>tak</td>\n",
- " <td>siÄ™</td>\n",
+ " <th>72</th>\n",
+ " <td>CORRECT</td>\n",
+ " <td>_</td>\n",
+ " <td>_</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>148</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>no</td>\n",
- " <td>-</td>\n",
+ " <th>73</th>\n",
+ " <td>DELETION</td>\n",
+ " <td>geogName</td>\n",
+ " <td></td>\n",
" </tr>\n",
" <tr>\n",
- " <th>149</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>dobrze</td>\n",
- " <td>dla</td>\n",
+ " <th>74</th>\n",
+ " <td>DELETION</td>\n",
+ " <td>geogName</td>\n",
+ " <td></td>\n",
" </tr>\n",
" <tr>\n",
- " <th>150</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>a</td>\n",
- " <td>mnie</td>\n",
+ " <th>75</th>\n",
+ " <td>CORRECT</td>\n",
+ " <td>_</td>\n",
+ " <td>_</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>151</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>Sielce</td>\n",
- " <td>trwało</td>\n",
+ " <th>76</th>\n",
+ " <td>CORRECT</td>\n",
+ " <td>_</td>\n",
+ " <td>_</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>152</th>\n",
+ " <th>77</th>\n",
" <td>CORRECT</td>\n",
- " <td>to</td>\n",
- " <td>to</td>\n",
+ " <td>_</td>\n",
+ " <td>_</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>153</th>\n",
- " <td>INSERTION</td>\n",
+ " <th>78</th>\n",
+ " <td>CORRECT</td>\n",
+ " <td>placeName</td>\n",
+ " <td>placeName</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>79</th>\n",
+ " <td>DELETION</td>\n",
+ " <td>_</td>\n",
" <td></td>\n",
- " <td>trzy</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>154</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>znaczy</td>\n",
- " <td>trzody</td>\n",
+ " <th>80</th>\n",
+ " <td>DELETION</td>\n",
+ " <td>_</td>\n",
+ " <td></td>\n",
" </tr>\n",
" <tr>\n",
- " <th>155</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>jaka</td>\n",
- " <td>ścięte</td>\n",
+ " <th>81</th>\n",
+ " <td>DELETION</td>\n",
+ " <td>_</td>\n",
+ " <td></td>\n",
" </tr>\n",
" <tr>\n",
- " <th>156</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>to</td>\n",
- " <td>tato</td>\n",
+ " <th>82</th>\n",
+ " <td>DELETION</td>\n",
+ " <td>_</td>\n",
+ " <td></td>\n",
" </tr>\n",
" <tr>\n",
- " <th>157</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>już</td>\n",
- " <td>taneczne</td>\n",
+ " <th>83</th>\n",
+ " <td>CORRECT</td>\n",
+ " <td>_</td>\n",
+ " <td>_</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>158</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>jest</td>\n",
- " <td><</td>\n",
+ " <th>84</th>\n",
+ " <td>CORRECT</td>\n",
+ " <td>_</td>\n",
+ " <td>_</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>159</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>dzielnica</td>\n",
- " <td>unk</td>\n",
+ " <th>85</th>\n",
+ " <td>CORRECT</td>\n",
+ " <td>_</td>\n",
+ " <td>_</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>160</th>\n",
+ " <th>86</th>\n",
" <td>SUBSTITUTION</td>\n",
- " <td>to</td>\n",
- " <td>></td>\n",
+ " <td>_</td>\n",
+ " <td>placeName</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>161</th>\n",
+ " <th>87</th>\n",
" <td>CORRECT</td>\n",
- " <td>ta</td>\n",
- " <td>ta</td>\n",
+ " <td>_</td>\n",
+ " <td>_</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>162</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>jest</td>\n",
- " <td>notatka</td>\n",
+ " <th>88</th>\n",
+ " <td>CORRECT</td>\n",
+ " <td>_</td>\n",
+ " <td>_</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>163</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>przy</td>\n",
- " <td>siÄ™</td>\n",
+ " <th>89</th>\n",
+ " <td>CORRECT</td>\n",
+ " <td>_</td>\n",
+ " <td>_</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>164</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>ulica</td>\n",
- " <td>tutaj</td>\n",
+ " <th>90</th>\n",
+ " <td>DELETION</td>\n",
+ " <td>geogName</td>\n",
+ " <td></td>\n",
" </tr>\n",
" <tr>\n",
- " <th>165</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>Gagarina</td>\n",
- " <td>także</td>\n",
+ " <th>91</th>\n",
+ " <td>DELETION</td>\n",
+ " <td>geogName</td>\n",
+ " <td></td>\n",
" </tr>\n",
" <tr>\n",
- " <th>166</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>a</td>\n",
- " <td>kilka</td>\n",
+ " <th>92</th>\n",
+ " <td>CORRECT</td>\n",
+ " <td>_</td>\n",
+ " <td>_</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>167</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>przy</td>\n",
- " <td>tutaj</td>\n",
+ " <th>93</th>\n",
+ " <td>CORRECT</td>\n",
+ " <td>_</td>\n",
+ " <td>_</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>168</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>ulicy</td>\n",
- " <td>trzy</td>\n",
+ " <th>94</th>\n",
+ " <td>CORRECT</td>\n",
+ " <td>_</td>\n",
+ " <td>_</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>169</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>Gagarina</td>\n",
- " <td>czy</td>\n",
+ " <th>95</th>\n",
+ " <td>CORRECT</td>\n",
+ " <td>_</td>\n",
+ " <td>_</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>170</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>czyli</td>\n",
- " <td>cztery</td>\n",
+ " <th>96</th>\n",
+ " <td>DELETION</td>\n",
+ " <td>orgName</td>\n",
+ " <td></td>\n",
" </tr>\n",
" <tr>\n",
- " <th>171</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>to</td>\n",
- " <td>dni</td>\n",
+ " <th>97</th>\n",
+ " <td>DELETION</td>\n",
+ " <td>orgName</td>\n",
+ " <td></td>\n",
" </tr>\n",
" <tr>\n",
- " <th>172</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>jest</td>\n",
- " <td><</td>\n",
+ " <th>98</th>\n",
+ " <td>CORRECT</td>\n",
+ " <td>_</td>\n",
+ " <td>_</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>173</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>tam</td>\n",
- " <td>unk</td>\n",
+ " <th>99</th>\n",
+ " <td>CORRECT</td>\n",
+ " <td>_</td>\n",
+ " <td>_</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>174</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>Mokotów</td>\n",
- " <td>></td>\n",
+ " <th>100</th>\n",
+ " <td>CORRECT</td>\n",
+ " <td>_</td>\n",
+ " <td>_</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>175</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>po</td>\n",
- " <td>płyty</td>\n",
+ " <th>101</th>\n",
+ " <td>CORRECT</td>\n",
+ " <td>_</td>\n",
+ " <td>_</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>176</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>prostu</td>\n",
- " <td>darin</td>\n",
+ " <th>102</th>\n",
+ " <td>CORRECT</td>\n",
+ " <td>_</td>\n",
+ " <td>_</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>177</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>tak</td>\n",
- " <td>nakryta</td>\n",
+ " <th>103</th>\n",
+ " <td>CORRECT</td>\n",
+ " <td>_</td>\n",
+ " <td>_</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>178</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>?</td>\n",
- " <td>plakatów</td>\n",
+ " <th>104</th>\n",
+ " <td>CORRECT</td>\n",
+ " <td>_</td>\n",
+ " <td>_</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>179</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>tak</td>\n",
- " <td>pod</td>\n",
+ " <th>105</th>\n",
+ " <td>CORRECT</td>\n",
+ " <td>_</td>\n",
+ " <td>_</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>180</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>Siekierki</td>\n",
- " <td>hutach</td>\n",
+ " <th>106</th>\n",
+ " <td>CORRECT</td>\n",
+ " <td>_</td>\n",
+ " <td>_</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>181</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>Mokotów</td>\n",
- " <td>siekierkowskÄ…</td>\n",
+ " <th>107</th>\n",
+ " <td>CORRECT</td>\n",
+ " <td>_</td>\n",
+ " <td>_</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>182</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>a</td>\n",
- " <td><</td>\n",
+ " <th>108</th>\n",
+ " <td>CORRECT</td>\n",
+ " <td>_</td>\n",
+ " <td>_</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>183</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>Siekierki</td>\n",
- " <td>unk</td>\n",
+ " <th>109</th>\n",
+ " <td>CORRECT</td>\n",
+ " <td>_</td>\n",
+ " <td>_</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>184</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>Mokotów</td>\n",
- " <td>></td>\n",
+ " <th>110</th>\n",
+ " <td>CORRECT</td>\n",
+ " <td>_</td>\n",
+ " <td>_</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>185</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>i</td>\n",
- " <td>a</td>\n",
+ " <th>111</th>\n",
+ " <td>CORRECT</td>\n",
+ " <td>_</td>\n",
+ " <td>_</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>186</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>tam</td>\n",
- " <td>siekierki</td>\n",
+ " <th>112</th>\n",
+ " <td>CORRECT</td>\n",
+ " <td>_</td>\n",
+ " <td>_</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>187</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>jak</td>\n",
- " <td>hoszowski</td>\n",
+ " <th>113</th>\n",
+ " <td>CORRECT</td>\n",
+ " <td>_</td>\n",
+ " <td>_</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>188</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>pani</td>\n",
- " <td>czytelnik</td>\n",
+ " <th>114</th>\n",
+ " <td>CORRECT</td>\n",
+ " <td>_</td>\n",
+ " <td>_</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>189</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>wysiÄ…dzie</td>\n",
- " <td>wyszedł</td>\n",
+ " <th>115</th>\n",
+ " <td>CORRECT</td>\n",
+ " <td>_</td>\n",
+ " <td>_</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>190</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>to</td>\n",
- " <td>od</td>\n",
+ " <th>116</th>\n",
+ " <td>CORRECT</td>\n",
+ " <td>_</td>\n",
+ " <td>_</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>191</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>trza</td>\n",
- " <td>swoich</td>\n",
+ " <th>117</th>\n",
+ " <td>DELETION</td>\n",
+ " <td>placeName</td>\n",
+ " <td></td>\n",
" </tr>\n",
" <tr>\n",
- " <th>192</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>wejść</td>\n",
- " <td>kolegów</td>\n",
+ " <th>118</th>\n",
+ " <td>DELETION</td>\n",
+ " <td>placeName</td>\n",
+ " <td></td>\n",
" </tr>\n",
" <tr>\n",
- " <th>193</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>w</td>\n",
- " <td>uliczek</td>\n",
+ " <th>119</th>\n",
+ " <td>CORRECT</td>\n",
+ " <td>_</td>\n",
+ " <td>_</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>194</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>lewo</td>\n",
- " <td><</td>\n",
+ " <th>120</th>\n",
+ " <td>CORRECT</td>\n",
+ " <td>_</td>\n",
+ " <td>_</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>195</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>w</td>\n",
- " <td>unk</td>\n",
+ " <th>121</th>\n",
+ " <td>CORRECT</td>\n",
+ " <td>_</td>\n",
+ " <td>_</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>196</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>ulicÄ™</td>\n",
- " <td>></td>\n",
+ " <th>122</th>\n",
+ " <td>CORRECT</td>\n",
+ " <td>_</td>\n",
+ " <td>_</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>197</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>Nehru</td>\n",
- " <td>od</td>\n",
+ " <th>123</th>\n",
+ " <td>CORRECT</td>\n",
+ " <td>_</td>\n",
+ " <td>_</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>198</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>i</td>\n",
- " <td><</td>\n",
+ " <th>124</th>\n",
+ " <td>CORRECT</td>\n",
+ " <td>_</td>\n",
+ " <td>_</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>199</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>od</td>\n",
- " <td>unk</td>\n",
+ " <th>125</th>\n",
+ " <td>CORRECT</td>\n",
+ " <td>_</td>\n",
+ " <td>_</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>200</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>Nehru</td>\n",
- " <td>></td>\n",
+ " <th>126</th>\n",
+ " <td>CORRECT</td>\n",
+ " <td>_</td>\n",
+ " <td>_</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>201</th>\n",
+ " <th>127</th>\n",
" <td>CORRECT</td>\n",
- " <td>odchodzi</td>\n",
- " <td>odchodzi</td>\n",
+ " <td>_</td>\n",
+ " <td>_</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>202</th>\n",
- " <td>INSERTION</td>\n",
- " <td></td>\n",
- " <td>służy</td>\n",
+ " <th>128</th>\n",
+ " <td>CORRECT</td>\n",
+ " <td>_</td>\n",
+ " <td>_</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>203</th>\n",
- " <td>INSERTION</td>\n",
+ " <th>129</th>\n",
+ " <td>DELETION</td>\n",
+ " <td>geogName</td>\n",
" <td></td>\n",
- " <td>nie</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>204</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>Zwierzyniecka</td>\n",
- " <td>tylko</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>205</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>w</td>\n",
- " <td><</td>\n",
+ " <th>130</th>\n",
+ " <td>CORRECT</td>\n",
+ " <td>_</td>\n",
+ " <td>_</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>206</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>lewo</td>\n",
- " <td>unk</td>\n",
+ " <th>131</th>\n",
+ " <td>CORRECT</td>\n",
+ " <td>_</td>\n",
+ " <td>_</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>207</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>w</td>\n",
- " <td>></td>\n",
+ " <th>132</th>\n",
+ " <td>CORRECT</td>\n",
+ " <td>_</td>\n",
+ " <td>_</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>208</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>lewo</td>\n",
- " <td>na</td>\n",
+ " <th>133</th>\n",
+ " <td>CORRECT</td>\n",
+ " <td>_</td>\n",
+ " <td>_</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>209</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>i</td>\n",
- " <td>ulicach</td>\n",
+ " <th>134</th>\n",
+ " <td>CORRECT</td>\n",
+ " <td>_</td>\n",
+ " <td>_</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>210</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>ulica</td>\n",
- " <td><</td>\n",
+ " <th>135</th>\n",
+ " <td>CORRECT</td>\n",
+ " <td>time</td>\n",
+ " <td>time</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>211</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>Nehru</td>\n",
- " <td>unk</td>\n",
+ " <th>136</th>\n",
+ " <td>CORRECT</td>\n",
+ " <td>time</td>\n",
+ " <td>time</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>212</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>?</td>\n",
- " <td>></td>\n",
+ " <th>137</th>\n",
+ " <td>CORRECT</td>\n",
+ " <td>time</td>\n",
+ " <td>time</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>213</th>\n",
+ " <th>138</th>\n",
" <td>CORRECT</td>\n",
- " <td>tak</td>\n",
- " <td>tak</td>\n",
+ " <td>time</td>\n",
+ " <td>time</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>214</th>\n",
- " <td>INSERTION</td>\n",
+ " <th>139</th>\n",
+ " <td>DELETION</td>\n",
+ " <td>_</td>\n",
" <td></td>\n",
- " <td>numeru</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>215</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>Nehru</td>\n",
- " <td>krytykuje</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>216</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>dobrze</td>\n",
- " <td>pan</td>\n",
+ " <th>140</th>\n",
+ " <td>DELETION</td>\n",
+ " <td>_</td>\n",
+ " <td></td>\n",
" </tr>\n",
" <tr>\n",
- " <th>217</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>dziękuję</td>\n",
- " <td><</td>\n",
+ " <th>141</th>\n",
+ " <td>DELETION</td>\n",
+ " <td>_</td>\n",
+ " <td></td>\n",
" </tr>\n",
" <tr>\n",
- " <th>218</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>panu</td>\n",
- " <td>unk</td>\n",
+ " <th>142</th>\n",
+ " <td>DELETION</td>\n",
+ " <td>_</td>\n",
+ " <td></td>\n",
" </tr>\n",
" <tr>\n",
- " <th>219</th>\n",
+ " <th>143</th>\n",
" <td>SUBSTITUTION</td>\n",
- " <td>bardzo</td>\n",
- " <td>></td>\n",
+ " <td>_</td>\n",
+ " <td>time</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>220</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>proszÄ™</td>\n",
- " <td>badania</td>\n",
+ " <th>144</th>\n",
+ " <td>CORRECT</td>\n",
+ " <td>_</td>\n",
+ " <td>_</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>221</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>do</td>\n",
- " <td><</td>\n",
+ " <th>145</th>\n",
+ " <td>CORRECT</td>\n",
+ " <td>_</td>\n",
+ " <td>_</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>222</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>widzenia</td>\n",
- " <td>unk</td>\n",
+ " <th>146</th>\n",
+ " <td>CORRECT</td>\n",
+ " <td>_</td>\n",
+ " <td>_</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>223</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>do</td>\n",
- " <td>></td>\n",
+ " <th>147</th>\n",
+ " <td>CORRECT</td>\n",
+ " <td>_</td>\n",
+ " <td>_</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>224</th>\n",
- " <td>SUBSTITUTION</td>\n",
- " <td>widzenia</td>\n",
- " <td></td>\n",
+ " <th>148</th>\n",
+ " <td>CORRECT</td>\n",
+ " <td>_</td>\n",
+ " <td>_</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
@@ -11152,231 +9901,155 @@
],
"text/plain": [
" step_type reference_word_text hypothesis_word_text\n",
- "0 DELETION xxx \n",
- "1 DELETION dzień \n",
- "2 DELETION dobry \n",
- "3 SUBSTITUTION dzień niedobre\n",
- "4 SUBSTITUTION dobry n\n",
- "5 SUBSTITUTION proszÄ™ .\n",
- "6 SUBSTITUTION pana e\n",
- "7 SUBSTITUTION ja .\n",
- "8 SUBSTITUTION chciałam pracy\n",
- "9 SUBSTITUTION siÄ™ a\n",
- "10 SUBSTITUTION dowiedzieć to\n",
- "11 SUBSTITUTION bo długo\n",
- "12 CORRECT nie nie\n",
- "13 SUBSTITUTION bardzo było\n",
- "14 SUBSTITUTION wiem to\n",
- "15 SUBSTITUTION gdzie dziecko\n",
- "16 SUBSTITUTION znajduje czuje\n",
- "17 CORRECT siÄ™ siÄ™\n",
- "18 DELETION ulica \n",
- "19 SUBSTITUTION Zwierzyniecka równie\n",
- "20 SUBSTITUTION i szybko\n",
- "21 CORRECT jak jak\n",
- "22 DELETION dojechać \n",
- "23 DELETION z \n",
- "24 DELETION Bródna \n",
- "25 DELETION na \n",
- "26 SUBSTITUTION przykład to\n",
- "27 SUBSTITUTION ? cecha\n",
- "28 SUBSTITUTION na brud\n",
- "29 SUBSTITUTION ZwierzynieckÄ… ta\n",
- "30 CORRECT na na\n",
- "31 DELETION ZwierzynieckÄ… \n",
- "32 DELETION a \n",
- "33 DELETION z \n",
- "34 SUBSTITUTION Bródna przykład\n",
- "35 SUBSTITUTION z siÄ™\n",
- "36 SUBSTITUTION którego ostatnio\n",
- "37 SUBSTITUTION miejsca inżynierowie\n",
- "38 SUBSTITUTION ? i\n",
- "39 SUBSTITUTION z brudno\n",
- "40 SUBSTITUTION Bródna straszliwy\n",
- "41 SUBSTITUTION to szok\n",
- "42 SUBSTITUTION jest brodatego\n",
- "43 CORRECT ulica ulica\n",
- "44 DELETION Wyszogrodzka \n",
- "45 SUBSTITUTION tu wyszogrodzka\n",
- "46 CORRECT przy przy\n",
- "47 DELETION Rembielińskiej \n",
- "48 DELETION czyli \n",
- "49 SUBSTITUTION przy rembielińskiej\n",
- "50 SUBSTITUTION tramwajach ich\n",
- "51 SUBSTITUTION tak cztero\n",
- "52 SUBSTITUTION ? oto\n",
- "53 SUBSTITUTION przy ta\n",
- "54 SUBSTITUTION tramwajach jak\n",
- "55 CORRECT tak tak\n",
- "56 DELETION może \n",
- "57 SUBSTITUTION pani dużo\n",
- "58 SUBSTITUTION poczeka punktów\n",
- "59 SUBSTITUTION sprawdzÄ™ <\n",
- "60 SUBSTITUTION dobrze unk\n",
- "61 SUBSTITUTION dobrze >\n",
- "62 SUBSTITUTION pani oni\n",
- "63 SUBSTITUTION sobie żeby\n",
- "64 SUBSTITUTION podjedzie podróży\n",
- "65 CORRECT tramwajem tramwajem\n",
- "66 CORRECT do do\n",
- "67 SUBSTITUTION Ronda rondo\n",
- "68 CORRECT Żaba Żaba\n",
- "69 SUBSTITUTION tak <\n",
- "70 SUBSTITUTION od unk\n",
- "71 SUBSTITUTION Ronda >\n",
- "72 SUBSTITUTION Żaba toronto\n",
- "73 CORRECT już już\n",
- "74 CORRECT sto sto\n",
- "75 CORRECT sześćdziesiąt sześćdziesiąt\n",
- "76 DELETION dwa \n",
- "77 SUBSTITUTION jest wojsk\n",
- "78 CORRECT sto sto\n",
- "79 CORRECT sześćdziesiąt sześćdziesiąt\n",
- "80 INSERTION ta\n",
- "81 SUBSTITUTION dwa <\n",
- "82 SUBSTITUTION tak unk\n",
- "83 SUBSTITUTION i >\n",
- "84 SUBSTITUTION sto trzysta\n",
- "85 CORRECT sześćdziesiąt sześćdziesiąt\n",
- "86 SUBSTITUTION dwa rataja\n",
- "87 SUBSTITUTION tam <\n",
- "88 SUBSTITUTION dojadÄ™ unk\n",
- "89 SUBSTITUTION do >\n",
- "90 CORRECT tej tej\n",
- "91 INSERTION <\n",
- "92 SUBSTITUTION ulicy unk\n",
- "93 SUBSTITUTION tak >\n",
- "94 CORRECT może może\n",
- "95 SUBSTITUTION pani pojawić\n",
- "96 SUBSTITUTION wysiąść się\n",
- "97 SUBSTITUTION na trzy\n",
- "98 SUBSTITUTION przystanku stÄ…d\n",
- "99 SUBSTITUTION Bartycka <\n",
- "100 SUBSTITUTION albo unk\n",
- "101 SUBSTITUTION Sielce >\n",
- "102 SUBSTITUTION Bartycka <\n",
- "103 SUBSTITUTION albo unk\n",
- "104 SUBSTITUTION ? >\n",
- "105 SUBSTITUTION Sielce <\n",
- "106 SUBSTITUTION Sielce unk\n",
- "107 SUBSTITUTION tak >\n",
- "108 SUBSTITUTION ? <\n",
- "109 SUBSTITUTION tak unk\n",
- "110 SUBSTITUTION aha >\n",
- "111 SUBSTITUTION i <\n",
- "112 SUBSTITUTION tam unk\n",
- "113 SUBSTITUTION w >\n",
- "114 SUBSTITUTION pobliżu berty\n",
- "115 SUBSTITUTION jest coraz\n",
- "116 SUBSTITUTION ta szybciej\n",
- "117 SUBSTITUTION ulica bartycka\n",
- "118 SUBSTITUTION tak <\n",
- "119 SUBSTITUTION ? unk\n",
- "120 SUBSTITUTION a >\n",
- "121 SUBSTITUTION Zwierzyniecka trzema\n",
- "122 SUBSTITUTION wysoki trzeba\n",
- "123 SUBSTITUTION numer siÄ™\n",
- "124 SUBSTITUTION ma trochÄ™\n",
- "125 SUBSTITUTION pani tak\n",
- "126 SUBSTITUTION ? jak\n",
- "127 SUBSTITUTION Zwierzyniecka i\n",
- "128 SUBSTITUTION zaraz te\n",
- "129 SUBSTITUTION momencik plany\n",
- "130 SUBSTITUTION osiem stały\n",
- "131 SUBSTITUTION A siÄ™\n",
- "132 SUBSTITUTION Zwierzyniecka słynne\n",
- "133 SUBSTITUTION to ciężko\n",
- "134 SUBSTITUTION to dyszÄ…c\n",
- "135 SUBSTITUTION przy i\n",
- "136 SUBSTITUTION Sielce numer\n",
- "137 SUBSTITUTION trza ewidencyjny\n",
- "138 SUBSTITUTION wysiąść <\n",
- "139 SUBSTITUTION przy unk\n",
- "140 SUBSTITUTION Sielce >\n",
- "141 SUBSTITUTION tak nowy\n",
- "142 SUBSTITUTION ? typ\n",
- "143 SUBSTITUTION tak <\n",
- "144 SUBSTITUTION przystanek unk\n",
- "145 SUBSTITUTION Sielce >\n",
- "146 SUBSTITUTION aha -\n",
- "147 SUBSTITUTION tak siÄ™\n",
- "148 SUBSTITUTION no -\n",
- "149 SUBSTITUTION dobrze dla\n",
- "150 SUBSTITUTION a mnie\n",
- "151 SUBSTITUTION Sielce trwało\n",
- "152 CORRECT to to\n",
- "153 INSERTION trzy\n",
- "154 SUBSTITUTION znaczy trzody\n",
- "155 SUBSTITUTION jaka ścięte\n",
- "156 SUBSTITUTION to tato\n",
- "157 SUBSTITUTION już taneczne\n",
- "158 SUBSTITUTION jest <\n",
- "159 SUBSTITUTION dzielnica unk\n",
- "160 SUBSTITUTION to >\n",
- "161 CORRECT ta ta\n",
- "162 SUBSTITUTION jest notatka\n",
- "163 SUBSTITUTION przy siÄ™\n",
- "164 SUBSTITUTION ulica tutaj\n",
- "165 SUBSTITUTION Gagarina także\n",
- "166 SUBSTITUTION a kilka\n",
- "167 SUBSTITUTION przy tutaj\n",
- "168 SUBSTITUTION ulicy trzy\n",
- "169 SUBSTITUTION Gagarina czy\n",
- "170 SUBSTITUTION czyli cztery\n",
- "171 SUBSTITUTION to dni\n",
- "172 SUBSTITUTION jest <\n",
- "173 SUBSTITUTION tam unk\n",
- "174 SUBSTITUTION Mokotów >\n",
- "175 SUBSTITUTION po płyty\n",
- "176 SUBSTITUTION prostu darin\n",
- "177 SUBSTITUTION tak nakryta\n",
- "178 SUBSTITUTION ? plakatów\n",
- "179 SUBSTITUTION tak pod\n",
- "180 SUBSTITUTION Siekierki hutach\n",
- "181 SUBSTITUTION Mokotów siekierkowską\n",
- "182 SUBSTITUTION a <\n",
- "183 SUBSTITUTION Siekierki unk\n",
- "184 SUBSTITUTION Mokotów >\n",
- "185 SUBSTITUTION i a\n",
- "186 SUBSTITUTION tam siekierki\n",
- "187 SUBSTITUTION jak hoszowski\n",
- "188 SUBSTITUTION pani czytelnik\n",
- "189 SUBSTITUTION wysiądzie wyszedł\n",
- "190 SUBSTITUTION to od\n",
- "191 SUBSTITUTION trza swoich\n",
- "192 SUBSTITUTION wejść kolegów\n",
- "193 SUBSTITUTION w uliczek\n",
- "194 SUBSTITUTION lewo <\n",
- "195 SUBSTITUTION w unk\n",
- "196 SUBSTITUTION ulicÄ™ >\n",
- "197 SUBSTITUTION Nehru od\n",
- "198 SUBSTITUTION i <\n",
- "199 SUBSTITUTION od unk\n",
- "200 SUBSTITUTION Nehru >\n",
- "201 CORRECT odchodzi odchodzi\n",
- "202 INSERTION służy\n",
- "203 INSERTION nie\n",
- "204 SUBSTITUTION Zwierzyniecka tylko\n",
- "205 SUBSTITUTION w <\n",
- "206 SUBSTITUTION lewo unk\n",
- "207 SUBSTITUTION w >\n",
- "208 SUBSTITUTION lewo na\n",
- "209 SUBSTITUTION i ulicach\n",
- "210 SUBSTITUTION ulica <\n",
- "211 SUBSTITUTION Nehru unk\n",
- "212 SUBSTITUTION ? >\n",
- "213 CORRECT tak tak\n",
- "214 INSERTION numeru\n",
- "215 SUBSTITUTION Nehru krytykuje\n",
- "216 SUBSTITUTION dobrze pan\n",
- "217 SUBSTITUTION dziękuję <\n",
- "218 SUBSTITUTION panu unk\n",
- "219 SUBSTITUTION bardzo >\n",
- "220 SUBSTITUTION proszÄ™ badania\n",
- "221 SUBSTITUTION do <\n",
- "222 SUBSTITUTION widzenia unk\n",
- "223 SUBSTITUTION do >\n",
- "224 SUBSTITUTION widzenia "
+ "0 DELETION _ \n",
+ "1 DELETION _ \n",
+ "2 DELETION _ \n",
+ "3 DELETION _ \n",
+ "4 DELETION _ \n",
+ "5 CORRECT _ _\n",
+ "6 CORRECT _ _\n",
+ "7 CORRECT _ _\n",
+ "8 CORRECT _ _\n",
+ "9 CORRECT _ _\n",
+ "10 CORRECT _ _\n",
+ "11 CORRECT _ _\n",
+ "12 CORRECT _ _\n",
+ "13 CORRECT _ _\n",
+ "14 CORRECT _ _\n",
+ "15 CORRECT _ _\n",
+ "16 CORRECT _ _\n",
+ "17 CORRECT _ _\n",
+ "18 DELETION geogName \n",
+ "19 DELETION geogName \n",
+ "20 DELETION geogName \n",
+ "21 CORRECT _ _\n",
+ "22 CORRECT _ _\n",
+ "23 DELETION placeName \n",
+ "24 CORRECT _ _\n",
+ "25 CORRECT _ _\n",
+ "26 CORRECT _ _\n",
+ "27 CORRECT _ _\n",
+ "28 CORRECT _ _\n",
+ "29 CORRECT _ _\n",
+ "30 CORRECT _ _\n",
+ "31 CORRECT _ _\n",
+ "32 DELETION orgName \n",
+ "33 CORRECT _ _\n",
+ "34 CORRECT _ _\n",
+ "35 CORRECT _ _\n",
+ "36 CORRECT _ _\n",
+ "37 CORRECT _ _\n",
+ "38 CORRECT _ _\n",
+ "39 CORRECT _ _\n",
+ "40 CORRECT _ _\n",
+ "41 CORRECT _ _\n",
+ "42 CORRECT _ _\n",
+ "43 DELETION geogName \n",
+ "44 DELETION geogName \n",
+ "45 CORRECT _ _\n",
+ "46 CORRECT placeName placeName\n",
+ "47 CORRECT _ _\n",
+ "48 CORRECT _ _\n",
+ "49 CORRECT _ _\n",
+ "50 DELETION placeName \n",
+ "51 CORRECT _ _\n",
+ "52 CORRECT _ _\n",
+ "53 CORRECT _ _\n",
+ "54 CORRECT _ _\n",
+ "55 CORRECT _ _\n",
+ "56 CORRECT _ _\n",
+ "57 DELETION geogName \n",
+ "58 CORRECT _ _\n",
+ "59 CORRECT _ _\n",
+ "60 CORRECT _ _\n",
+ "61 CORRECT _ _\n",
+ "62 CORRECT _ _\n",
+ "63 CORRECT _ _\n",
+ "64 DELETION persName \n",
+ "65 CORRECT _ _\n",
+ "66 CORRECT _ _\n",
+ "67 CORRECT _ _\n",
+ "68 CORRECT _ _\n",
+ "69 CORRECT _ _\n",
+ "70 CORRECT _ _\n",
+ "71 CORRECT _ _\n",
+ "72 CORRECT _ _\n",
+ "73 DELETION geogName \n",
+ "74 DELETION geogName \n",
+ "75 CORRECT _ _\n",
+ "76 CORRECT _ _\n",
+ "77 CORRECT _ _\n",
+ "78 CORRECT placeName placeName\n",
+ "79 DELETION _ \n",
+ "80 DELETION _ \n",
+ "81 DELETION _ \n",
+ "82 DELETION _ \n",
+ "83 CORRECT _ _\n",
+ "84 CORRECT _ _\n",
+ "85 CORRECT _ _\n",
+ "86 SUBSTITUTION _ placeName\n",
+ "87 CORRECT _ _\n",
+ "88 CORRECT _ _\n",
+ "89 CORRECT _ _\n",
+ "90 DELETION geogName \n",
+ "91 DELETION geogName \n",
+ "92 CORRECT _ _\n",
+ "93 CORRECT _ _\n",
+ "94 CORRECT _ _\n",
+ "95 CORRECT _ _\n",
+ "96 DELETION orgName \n",
+ "97 DELETION orgName \n",
+ "98 CORRECT _ _\n",
+ "99 CORRECT _ _\n",
+ "100 CORRECT _ _\n",
+ "101 CORRECT _ _\n",
+ "102 CORRECT _ _\n",
+ "103 CORRECT _ _\n",
+ "104 CORRECT _ _\n",
+ "105 CORRECT _ _\n",
+ "106 CORRECT _ _\n",
+ "107 CORRECT _ _\n",
+ "108 CORRECT _ _\n",
+ "109 CORRECT _ _\n",
+ "110 CORRECT _ _\n",
+ "111 CORRECT _ _\n",
+ "112 CORRECT _ _\n",
+ "113 CORRECT _ _\n",
+ "114 CORRECT _ _\n",
+ "115 CORRECT _ _\n",
+ "116 CORRECT _ _\n",
+ "117 DELETION placeName \n",
+ "118 DELETION placeName \n",
+ "119 CORRECT _ _\n",
+ "120 CORRECT _ _\n",
+ "121 CORRECT _ _\n",
+ "122 CORRECT _ _\n",
+ "123 CORRECT _ _\n",
+ "124 CORRECT _ _\n",
+ "125 CORRECT _ _\n",
+ "126 CORRECT _ _\n",
+ "127 CORRECT _ _\n",
+ "128 CORRECT _ _\n",
+ "129 DELETION geogName \n",
+ "130 CORRECT _ _\n",
+ "131 CORRECT _ _\n",
+ "132 CORRECT _ _\n",
+ "133 CORRECT _ _\n",
+ "134 CORRECT _ _\n",
+ "135 CORRECT time time\n",
+ "136 CORRECT time time\n",
+ "137 CORRECT time time\n",
+ "138 CORRECT time time\n",
+ "139 DELETION _ \n",
+ "140 DELETION _ \n",
+ "141 DELETION _ \n",
+ "142 DELETION _ \n",
+ "143 SUBSTITUTION _ time\n",
+ "144 CORRECT _ _\n",
+ "145 CORRECT _ _\n",
+ "146 CORRECT _ _\n",
+ "147 CORRECT _ _\n",
+ "148 CORRECT _ _"
]
},
"metadata": {},
@@ -46581,67 +45254,128 @@
},
{
"cell_type": "code",
- "execution_count": null,
+ "execution_count": 2,
"id": "17823c33-7065-43e6-9d2f-49a59fba26c1",
"metadata": {},
"outputs": [],
- "source": []
+ "source": [
+ "import spacy\n",
+ "nlp = spacy.load(\"pl_core_news_lg\")"
+ ]
},
{
"cell_type": "code",
- "execution_count": null,
+ "execution_count": 3,
"id": "e8fa6eb7-ec32-4284-9ff3-1de52e969cb5",
"metadata": {},
"outputs": [],
- "source": []
+ "source": [
+ "doc = nlp(\"Ala ma psa i kota\")"
+ ]
},
{
"cell_type": "code",
- "execution_count": null,
+ "execution_count": 16,
"id": "cb0d05d0-8eff-4ddd-900a-207e67c2afc0",
"metadata": {},
- "outputs": [],
- "source": []
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "persName 0 1\n"
+ ]
+ }
+ ],
+ "source": [
+ "for it in doc.ents:\n",
+ " print(it.label_, it.start, it.end)"
+ ]
},
{
"cell_type": "code",
- "execution_count": null,
+ "execution_count": 11,
"id": "5f008198-1ad3-4fe6-a904-7a0e1b4d0ade",
"metadata": {},
- "outputs": [],
- "source": []
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "5"
+ ]
+ },
+ "execution_count": 11,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "len(doc)"
+ ]
},
{
"cell_type": "code",
- "execution_count": null,
+ "execution_count": 18,
"id": "f2a7a1e7-c226-4fd9-873b-cada73a9d5fb",
"metadata": {},
"outputs": [],
- "source": []
+ "source": [
+ "arr = ['_' for it in range(len(doc))]"
+ ]
},
{
"cell_type": "code",
- "execution_count": null,
+ "execution_count": 20,
"id": "6206ac46-c803-4c9f-a9f9-91a1f60177bf",
"metadata": {},
"outputs": [],
- "source": []
+ "source": [
+ "for ent in doc.ents:\n",
+ " for itt in range(ent.start, ent.end):\n",
+ " arr[itt] = ent.label_"
+ ]
},
{
"cell_type": "code",
- "execution_count": null,
+ "execution_count": 15,
"id": "9756f1eb-7e95-4d8a-8d99-d2f664c4105f",
"metadata": {},
- "outputs": [],
- "source": []
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "[2]"
+ ]
+ },
+ "execution_count": 15,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "# list(range(2, 3))"
+ ]
},
{
"cell_type": "code",
- "execution_count": null,
+ "execution_count": 22,
"id": "3b286ac6-e2fd-421f-89eb-fb66233856f7",
"metadata": {},
- "outputs": [],
- "source": []
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "['persName', '_', '_', '_', '_']"
+ ]
+ },
+ "execution_count": 22,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "arr"
+ ]
},
{
"cell_type": "code",
--
GitLab