diff --git a/combo/data/api.py b/combo/data/api.py
index ab00da569b52d1973072a8b76d13540303f5d98d..240a8b3001bcebbb1a1bd82838a1930a3faecf03 100644
--- a/combo/data/api.py
+++ b/combo/data/api.py
@@ -41,7 +41,11 @@ class _TokenList(conllu.models.TokenList):
def sentence2conllu(sentence: Sentence, keep_semrel: bool = True) -> conllu.models.TokenList:
tokens = []
+ used_multiwords = set()
for token in sentence.tokens:
+ if token.multiword and token.multiword not in used_multiwords:
+ tokens.append(collections.OrderedDict(Token(idx=token.multiword[1], text=token.multiword[0]).as_dict(keep_semrel)))
+ used_multiwords.add(token.multiword)
token_dict = collections.OrderedDict(token.as_dict(keep_semrel))
tokens.append(token_dict)
# Range tokens must be tuple not list, this is conllu library requirement
@@ -76,7 +80,7 @@ def serialize_field(field: Any) -> str:
return '|'.join(fields)
if isinstance(field, tuple):
- return "".join([serialize_field(item) for item in field])
+ return "-".join([serialize_field(item) for item in field])
if isinstance(field, list):
if len(field[0]) != 2:
diff --git a/combo/data/dataset_readers/universal_dependencies_dataset_reader.py b/combo/data/dataset_readers/universal_dependencies_dataset_reader.py
index a3b040889671acbec754ed6ef2631181d6710156..d8f9d0e9b129e4fcbccb671dbc6ab4711a759663 100644
--- a/combo/data/dataset_readers/universal_dependencies_dataset_reader.py
+++ b/combo/data/dataset_readers/universal_dependencies_dataset_reader.py
@@ -133,9 +133,9 @@ class UniversalDependenciesDatasetReader(DatasetReader, ABC):
def text_to_instance(self, tree: conllu.models.TokenList) -> Instance:
fields_: Dict[str, Field] = {}
- tokens = [Token.from_conllu_token(t) for t in tree if isinstance(t["id"], int)]
# features
+ tokens = tree
text_field = TextField(tokens, self.token_indexers)
fields_["sentence"] = text_field
diff --git a/combo/data/tokenizers/character_tokenizer.py b/combo/data/tokenizers/character_tokenizer.py
index b407e6fe6e9488d25b7e4e33e906ca9d58cb8092..2b3779bca954870061edea34396f3a66c18ca425 100644
--- a/combo/data/tokenizers/character_tokenizer.py
+++ b/combo/data/tokenizers/character_tokenizer.py
@@ -53,7 +53,9 @@ class CharacterTokenizer(Tokenizer):
self._start_tokens.reverse()
self._end_tokens = end_tokens or []
- def tokenize(self, text: str) -> List[Token]:
+ def tokenize(self, text: Union[str, Token]) -> List[Token]:
+ if isinstance(text, Token):
+ text = text.text
if self._lowercase_characters:
text = text.lower()
if self._byte_encoding is not None:
diff --git a/combo/data/tokenizers/lambo_tokenizer.py b/combo/data/tokenizers/lambo_tokenizer.py
index 684295814fb2a022692bedc37dd39751317711da..c5bb322f7377f8d608148d9697e75a95d81fb62b 100644
--- a/combo/data/tokenizers/lambo_tokenizer.py
+++ b/combo/data/tokenizers/lambo_tokenizer.py
@@ -1,4 +1,4 @@
-from typing import List, Optional
+from typing import Iterator, List, Optional
from lambo.segmenter.lambo import Lambo
@@ -7,6 +7,34 @@ from combo.config.from_parameters import register_arguments
from combo.data.tokenizers.token import Token
from combo.data.tokenizers.tokenizer import Tokenizer
+SPLIT_LEVELS = ["TURN", "SENTENCE", "NONE"]
+DEFAULT_SPLIT_LEVEL = "SENTENCE"
+
+IDX = 0
+
+
+def _token_idx() -> Iterator[int]:
+ global IDX
+ IDX += 1
+ yield IDX
+
+
+def _reset_idx():
+ global IDX
+ IDX = 0
+
+
+def _sentence_tokens(token: Token,
+ split_subwords: Optional[bool] = None) -> List[Token]:
+ if split_subwords and len(token.subwords) > 0:
+ subword_idxs = [next(_token_idx()) for _ in range(len(token.subwords))]
+ multiword = (token.text, (subword_idxs[0], subword_idxs[1]))
+ tokens = [Token(idx=s_idx, text=subword, multiword=multiword) for (s_idx, subword)
+ in zip(subword_idxs, token.subwords)]
+ return tokens
+ else:
+ return [Token(idx=next(_token_idx()), text=token.text)]
+
@Registry.register('lambo_tokenizer')
class LamboTokenizer(Tokenizer):
@@ -14,40 +42,71 @@ class LamboTokenizer(Tokenizer):
def __init__(
self,
language: str = "English",
- default_turns: bool = False,
- default_split_subwords: bool = False
+ default_split_level: str = DEFAULT_SPLIT_LEVEL,
+ default_split_subwords: bool = True
):
self._language = language
self.__tokenizer = Lambo.get(language)
- self.__default_turns = default_turns
+ self.__default_split_level = default_split_level.upper()
+
self.__default_split_subwords = default_split_subwords
- def tokenize(self, text: str) -> List[Token]:
+ def tokenize(self,
+ text: str,
+ split_level: Optional[str] = None,
+ split_subwords: Optional[bool] = None,
+ multiwords: Optional[bool] = None) -> List[List[Token]]:
"""
Simple tokenization - ignoring the sentence splits
:param text:
+ :param split_level: split on turns, sentences, or no splitting (return one list of tokens)
+ :param split_subwords: split subwords into separate tokens (e.g. can't into ca, n't)
:return:
"""
+ _reset_idx()
document = self.__tokenizer.segment(text)
tokens = []
- for turn in document.turns:
- for sentence in turn.sentences:
- for token in sentence.tokens:
- tokens.append(Token(token.text, subwords=token.subwords))
+ split_level = split_level if split_level is not None else self.__default_split_level
+ split_subwords = split_subwords if split_subwords is not None else self.__default_split_subwords
+
+ if split_level.upper() == "TURN":
+ for turn in document.turns:
+ sentence_tokens = []
+ for sentence in turn.sentences:
+ for token in sentence.tokens:
+ sentence_tokens.extend(_sentence_tokens(token, split_subwords))
+ tokens.append(sentence_tokens)
+ elif split_level.upper() == "SENTENCE":
+ for turn in document.turns:
+ for sentence in turn.sentences:
+ sentence_tokens = []
+ for token in sentence.tokens:
+ sentence_tokens.extend(_sentence_tokens(token, split_subwords))
+ tokens.append(sentence_tokens)
+ else:
+ for turn in document.turns:
+ for sentence in turn.sentences:
+ for token in sentence.tokens:
+ tokens.extend(_sentence_tokens(token, split_subwords))
+ tokens = [tokens]
return tokens
- def segment(self, text: str, turns: Optional[bool] = None, split_subwords: Optional[bool] = None) -> List[List[str]]:
+ def segment(self,
+ text: str,
+ turns: Optional[bool] = None,
+ split_subwords: Optional[bool] = None) -> List[List[str]]:
"""
- Full segmentation - segment into sentences.
+ Full segmentation - segment into sentences and return a list of strings.
:param text:
:param turns: segment into sentences by splitting on sentences or on turns. Default: sentences.
+ :param split_subwords: split subwords into separate tokens (e.g. can't into ca, n't)
:return:
"""
- turns = turns or self.__default_turns
- split_subwords = split_subwords or self.__default_split_subwords
+ turns = turns if turns is not None else self.__default_split_level.upper() == "TURNS"
+ split_subwords = split_subwords if split_subwords is not None else self.__default_split_subwords
document = self.__tokenizer.segment(text)
sentences = []
diff --git a/combo/data/tokenizers/token.py b/combo/data/tokenizers/token.py
index 16c3a8e57131de512201fc27981d363d7fa7e79b..319a5bd873bba1140d26f899d292d42f524b4317 100644
--- a/combo/data/tokenizers/token.py
+++ b/combo/data/tokenizers/token.py
@@ -29,6 +29,7 @@ class Token:
"deps",
"misc",
"subwords",
+ "multiword",
"semrel",
"embeddings",
"text_id",
@@ -47,6 +48,7 @@ class Token:
deps: Optional[str]
misc: Optional[str]
subwords: Optional[List[str]]
+ multiword: Optional[Tuple[str, Tuple[int, int]]]
semrel: Optional[str]
embeddings: Dict[str, List[float]]
text_id: Optional[int]
@@ -65,6 +67,7 @@ class Token:
deps: str = None,
misc: str = None,
subwords: List[str] = None,
+ multiword: Tuple[str, Tuple[int, int]] = None,
semrel: str = None,
embeddings: Dict[str, List[float]] = None,
text_id: int = None,
@@ -83,6 +86,7 @@ class Token:
self.deps = deps
self.misc = misc
self.subwords = subwords if subwords else []
+ self.multiword = multiword
self.semrel = semrel
if embeddings is None:
@@ -109,7 +113,7 @@ class Token:
return repr
def __str__(self):
- return self.text
+ return str(self.text)
def __repr__(self):
return self.__str__()
diff --git a/combo/predict.py b/combo/predict.py
index 74c1ca57ddd5110d63e00130ebd05c6a492c9be5..c4f507bb6a2aeb2ed1400a5abd24b7db773694ec 100644
--- a/combo/predict.py
+++ b/combo/predict.py
@@ -11,7 +11,7 @@ from combo import data
from combo.common import util
from combo.config import Registry
from combo.config.from_parameters import register_arguments
-from combo.data import Instance, conllu2sentence, tokens2conllu, sentence2conllu
+from combo.data import Instance, conllu2sentence, sentence2conllu
from combo.data.dataset_loaders.dataset_loader import TensorDict
from combo.data.dataset_readers.dataset_reader import DatasetReader
from combo.data.instance import JsonDict
@@ -20,6 +20,7 @@ from combo.modules.archival import load_archive
from combo.predictors import PredictorModule
from combo.utils import download, graph
from combo.modules.model import Model
+from combo.data import Token
logger = logging.getLogger(__name__)
@@ -72,16 +73,18 @@ class COMBO(PredictorModule):
def configure_optimizers(self) -> Any:
pass
- def predict(self, sentence: Union[str, List[str], List[List[str]], List[data.Sentence]]):
+ def predict(self,
+ sentence: Union[str, List[str], List[List[str]], List[data.Sentence]],
+ **kwargs):
if isinstance(sentence, str):
- sentence = self.dataset_reader.tokenizer.segment(sentence)
+ sentence = self.dataset_reader.tokenizer.tokenize(sentence, **kwargs)
if isinstance(sentence, list):
if len(sentence) == 0:
return []
example = sentence[0]
sentences = sentence
- if isinstance(example, str) or isinstance(example, list):
+ if isinstance(example, Token) or (isinstance(example, list) and isinstance(example[0], Token)):
result = []
sentences = [self._to_input_json(s) for s in sentences]
for sentences_batch in util.lazy_groups_of(sentences, self.batch_size):
@@ -140,13 +143,14 @@ class COMBO(PredictorModule):
@overrides
def _json_to_instance(self, json_dict) -> Instance:
sentence = json_dict["sentence"]
+ # TODO: tokenize EVERYTHING, even if a list is passed?
if isinstance(sentence, str):
tokens = [t.text for t in self.tokenizer.tokenize(json_dict["sentence"])]
elif isinstance(sentence, list):
tokens = sentence
else:
raise ValueError("Input must be either string or list of strings.")
- return self.dataset_reader.text_to_instance(tokens2conllu(tokens))
+ return self.dataset_reader.text_to_instance(tokens)
@overrides
def load_line(self, line: str) -> JsonDict:
@@ -174,7 +178,7 @@ class COMBO(PredictorModule):
def _predictions_as_tree(self, predictions: Dict[str, Any], instance: Instance):
tree = instance.fields["metadata"]["input"]
field_names = instance.fields["metadata"]["field_names"]
- tree_tokens = [t for t in tree if isinstance(t["idx"], int)]
+ tree_tokens = [t for t in tree if isinstance(t["idx"], int) or isinstance(t["idx"], tuple)]
embeddings = {t["idx"]: {} for t in tree}
deprel_tree_distribution = None
deprel_label_distribution = None
diff --git a/setup.py b/setup.py
index 80e89b4c67e191040e373bf5b9bc8803c3c2d5d4..0aeb7ee93ea5f4322c43c22480996c971cb00d7d 100644
--- a/setup.py
+++ b/setup.py
@@ -29,7 +29,7 @@ REQUIREMENTS = [
setup(
name="combo-nlp",
- version="3.0.4",
+ version="3.1.0",
author="Maja Jablonska",
author_email="maja.jablonska@ipipan.waw.pl",
install_requires=REQUIREMENTS,
diff --git a/tests/data/data_readers/en_test.conllu b/tests/data/data_readers/en_test.conllu
new file mode 100644
index 0000000000000000000000000000000000000000..9618de1e7c831b86f358f3989651914a6940ec59
--- /dev/null
+++ b/tests/data/data_readers/en_test.conllu
@@ -0,0 +1,116 @@
+# newdoc id = weblog-blogspot.com_zentelligence_20040423000200_ENG_20040423_000200
+# sent_id = weblog-blogspot.com_zentelligence_20040423000200_ENG_20040423_000200-0001
+# newpar id = weblog-blogspot.com_zentelligence_20040423000200_ENG_20040423_000200-p0001
+# text = What if Google Morphed Into GoogleOS?
+1 What what PRON WP PronType=Int 0 root 0:root _
+2 if if SCONJ IN _ 4 mark 4:mark _
+3 Google Google PROPN NNP Number=Sing 4 nsubj 4:nsubj _
+4 Morphed morph VERB VBD Mood=Ind|Number=Sing|Person=3|Tense=Past|VerbForm=Fin 1 advcl 1:advcl:if _
+5 Into into ADP IN _ 6 case 6:case _
+6 GoogleOS GoogleOS PROPN NNP Number=Sing 4 obl 4:obl:into SpaceAfter=No
+7 ? ? PUNCT . _ 4 punct 4:punct _
+
+# sent_id = weblog-blogspot.com_zentelligence_20040423000200_ENG_20040423_000200-0002
+# text = What if Google expanded on its search-engine (and now e-mail) wares into a full-fledged operating system?
+1 What what PRON WP PronType=Int 0 root 0:root _
+2 if if SCONJ IN _ 4 mark 4:mark _
+3 Google Google PROPN NNP Number=Sing 4 nsubj 4:nsubj _
+4 expanded expand VERB VBD Mood=Ind|Number=Sing|Person=3|Tense=Past|VerbForm=Fin 1 advcl 1:advcl:if _
+5 on on ADP IN _ 15 case 15:case _
+6 its its PRON PRP$ Case=Gen|Gender=Neut|Number=Sing|Person=3|Poss=Yes|PronType=Prs 15 nmod:poss 15:nmod:poss _
+7 search search NOUN NN Number=Sing 9 compound 9:compound SpaceAfter=No
+8 - - PUNCT HYPH _ 7 punct 7:punct SpaceAfter=No
+9 engine engine NOUN NN Number=Sing 15 compound 15:compound _
+10 ( ( PUNCT -LRB- _ 13 punct 13:punct SpaceAfter=No
+11 and and CCONJ CC _ 13 cc 13:cc _
+12 now now ADV RB _ 13 advmod 13:advmod _
+13 e-mail e-mail NOUN NN Number=Sing 9 conj 9:conj:and|15:compound SpaceAfter=No
+14 ) ) PUNCT -RRB- _ 13 punct 13:punct _
+15 wares wares NOUN NNS Number=Plur 4 obl 4:obl:on _
+16 into into ADP IN _ 22 case 22:case _
+17 a a DET DT Definite=Ind|PronType=Art 22 det 22:det _
+18 full full ADV RB _ 20 advmod 20:advmod SpaceAfter=No
+19 - - PUNCT HYPH _ 18 punct 18:punct SpaceAfter=No
+20 fledged fledged ADJ JJ Degree=Pos 22 amod 22:amod _
+21 operating operating NOUN NN Number=Sing 22 compound 22:compound _
+22 system system NOUN NN Number=Sing 4 obl 4:obl:into SpaceAfter=No
+23 ? ? PUNCT . _ 4 punct 4:punct _
+
+# sent_id = weblog-blogspot.com_zentelligence_20040423000200_ENG_20040423_000200-0003
+# text = [via Microsoft Watch from Mary Jo Foley ]
+1 [ [ PUNCT -LRB- _ 4 punct 4:punct SpaceAfter=No
+2 via via ADP IN _ 4 case 4:case _
+3 Microsoft Microsoft PROPN NNP Number=Sing 4 compound 4:compound _
+4 Watch Watch PROPN NNP Number=Sing 0 root 0:root _
+5 from from ADP IN _ 6 case 6:case _
+6 Mary Mary PROPN NNP Number=Sing 4 nmod 4:nmod:from _
+7 Jo Jo PROPN NNP Number=Sing 6 flat 6:flat _
+8 Foley Foley PROPN NNP Number=Sing 6 flat 6:flat _
+9 ] ] PUNCT -RRB- _ 4 punct 4:punct _
+
+# newdoc id = weblog-blogspot.com_marketview_20050511222700_ENG_20050511_222700
+# sent_id = weblog-blogspot.com_marketview_20050511222700_ENG_20050511_222700-0001
+# newpar id = weblog-blogspot.com_marketview_20050511222700_ENG_20050511_222700-p0001
+# text = (And, by the way, is anybody else just a little nostalgic for the days when that was a good thing?)
+1 ( ( PUNCT -LRB- _ 14 punct 14:punct SpaceAfter=No
+2 And and CCONJ CC _ 14 cc 14:cc SpaceAfter=No
+3 , , PUNCT , _ 2 punct 2:punct _
+4 by by ADP IN _ 6 case 6:case _
+5 the the DET DT Definite=Def|PronType=Art 6 det 6:det _
+6 way way NOUN NN Number=Sing 14 obl 14:obl:by SpaceAfter=No
+7 , , PUNCT , _ 6 punct 6:punct _
+8 is be AUX VBZ Mood=Ind|Number=Sing|Person=3|Tense=Pres|VerbForm=Fin 14 cop 14:cop _
+9 anybody anybody PRON NN Number=Sing|PronType=Ind 14 nsubj 14:nsubj _
+10 else else ADJ JJ Degree=Pos 9 amod 9:amod _
+11 just just ADV RB _ 13 advmod 13:advmod _
+12 a a DET DT Definite=Ind|PronType=Art 13 det 13:det _
+13 little little ADJ JJ Degree=Pos 14 obl:npmod 14:obl:npmod _
+14 nostalgic nostalgic NOUN NN Number=Sing 0 root 0:root _
+15 for for ADP IN _ 17 case 17:case _
+16 the the DET DT Definite=Def|PronType=Art 17 det 17:det _
+17 days day NOUN NNS Number=Plur 14 nmod 14:nmod:for|23:obl:npmod _
+18 when when ADV WRB PronType=Rel 23 advmod 17:ref _
+19 that that PRON DT Number=Sing|PronType=Dem 23 nsubj 23:nsubj _
+20 was be AUX VBD Mood=Ind|Number=Sing|Person=3|Tense=Past|VerbForm=Fin 23 cop 23:cop _
+21 a a DET DT Definite=Ind|PronType=Art 23 det 23:det _
+22 good good ADJ JJ Degree=Pos 23 amod 23:amod _
+23 thing thing NOUN NN Number=Sing 17 acl:relcl 17:acl:relcl SpaceAfter=No
+24 ? ? PUNCT . _ 14 punct 14:punct SpaceAfter=No
+25 ) ) PUNCT -RRB- _ 14 punct 14:punct _
+
+# sent_id = weblog-blogspot.com_marketview_20050511222700_ENG_20050511_222700-0002
+# text = This BuzzMachine post argues that Google's rush toward ubiquity might backfire -- which we've all heard before, but it's particularly well-put in this post.
+1 This this DET DT Number=Sing|PronType=Dem 3 det 3:det _
+2 BuzzMachine BuzzMachine PROPN NNP Number=Sing 3 compound 3:compound _
+3 post post NOUN NN Number=Sing 4 nsubj 4:nsubj _
+4 argues argue VERB VBZ Mood=Ind|Number=Sing|Person=3|Tense=Pres|VerbForm=Fin 0 root 0:root _
+5 that that SCONJ IN _ 12 mark 12:mark _
+6-7 Google's _ _ _ _ _ _ _ _
+6 Google Google PROPN NNP Number=Sing 8 nmod:poss 8:nmod:poss _
+7 's 's PART POS _ 6 case 6:case _
+8 rush rush NOUN NN Number=Sing 12 nsubj 12:nsubj _
+9 toward toward ADP IN _ 10 case 10:case _
+10 ubiquity ubiquity NOUN NN Number=Sing 8 nmod 8:nmod:toward _
+11 might might AUX MD VerbForm=Fin 12 aux 12:aux _
+12 backfire backfire VERB VB VerbForm=Inf 4 ccomp 4:ccomp|18:ccomp _
+13 -- -- PUNCT , _ 18 punct 18:punct _
+14 which which PRON WDT PronType=Rel 18 obj 12:ref _
+15-16 we've _ _ _ _ _ _ _ _
+15 we we PRON PRP Case=Nom|Number=Plur|Person=1|PronType=Prs 18 nsubj 18:nsubj _
+16 've have AUX VBP Mood=Ind|Number=Plur|Person=1|Tense=Pres|VerbForm=Fin 18 aux 18:aux _
+17 all all ADV RB _ 18 advmod 18:advmod _
+18 heard hear VERB VBN Tense=Past|VerbForm=Part 12 advcl:relcl 12:advcl:relcl _
+19 before before ADV RB _ 18 advmod 18:advmod SpaceAfter=No
+20 , , PUNCT , _ 27 punct 27:punct _
+21 but but CCONJ CC _ 27 cc 27:cc _
+22-23 it's _ _ _ _ _ _ _ _
+22 it it PRON PRP Case=Nom|Gender=Neut|Number=Sing|Person=3|PronType=Prs 27 nsubj:pass 27:nsubj:pass _
+23 's be AUX VBZ Mood=Ind|Number=Sing|Person=3|Tense=Pres|VerbForm=Fin 27 aux:pass 27:aux:pass _
+24 particularly particularly ADV RB _ 27 advmod 27:advmod _
+25 well well ADV RB Degree=Pos 27 advmod 27:advmod SpaceAfter=No
+26 - - PUNCT HYPH _ 25 punct 25:punct SpaceAfter=No
+27 put put VERB VBN Tense=Past|VerbForm=Part|Voice=Pass 4 conj 4:conj:but _
+28 in in ADP IN _ 30 case 30:case _
+29 this this DET DT Number=Sing|PronType=Dem 30 det 30:det _
+30 post post NOUN NN Number=Sing 27 obl 27:obl:in SpaceAfter=No
+31 . . PUNCT . _ 4 punct 4:punct _
diff --git a/tests/data/data_readers/test_universal_dependencies_dataset_reader.py b/tests/data/data_readers/test_universal_dependencies_dataset_reader.py
index 39cb0fa1dfd87d51346295f9bb83f383d149f7ea..b3292ee0a915a2a11e19cfb472f084fbc18b3985 100644
--- a/tests/data/data_readers/test_universal_dependencies_dataset_reader.py
+++ b/tests/data/data_readers/test_universal_dependencies_dataset_reader.py
@@ -1,30 +1,30 @@
import unittest
import os
-from combo.data import UniversalDependenciesDatasetReader
+from combo.data import UniversalDependenciesDatasetReader, LamboTokenizer
class UniversalDependenciesDatasetReaderTest(unittest.TestCase):
def test_read_all_tokens(self):
t = UniversalDependenciesDatasetReader()
- tokens = [token for token in t.read(os.path.join(os.path.dirname(__file__), 'tl_trg-ud-test.conllu'))]
- self.assertEqual(len(tokens), 128)
+ tokens = [token for token in t.read(os.path.join(os.path.dirname(__file__), 'en_test.conllu'))]
+ self.assertEqual(len(tokens), 5)
def test_read_text(self):
t = UniversalDependenciesDatasetReader()
- token = next(iter(t.read(os.path.join(os.path.dirname(__file__), 'tl_trg-ud-test.conllu'))))
+ token = next(iter(t.read(os.path.join(os.path.dirname(__file__), 'en_test.conllu'))))
self.assertListEqual([t.text for t in token['sentence'].tokens],
- ['Gumising', 'ang', 'bata', '.'])
+ ['What', 'if', 'Google', 'Morphed', 'Into', 'GoogleOS', '?'])
def test_read_deprel(self):
t = UniversalDependenciesDatasetReader()
- token = next(iter(t.read(os.path.join(os.path.dirname(__file__), 'tl_trg-ud-test.conllu'))))
+ token = next(iter(t.read(os.path.join(os.path.dirname(__file__), 'en_test.conllu'))))
self.assertListEqual(token['deprel'].labels,
- ['root', 'case', 'nsubj', 'punct'])
+ ['root', 'mark', 'nsubj', 'advcl', 'case', 'obl', 'punct'])
def test_read_upostag(self):
t = UniversalDependenciesDatasetReader()
- token = next(iter(t.read(os.path.join(os.path.dirname(__file__), 'tl_trg-ud-test.conllu'))))
+ token = next(iter(t.read(os.path.join(os.path.dirname(__file__), 'en_test.conllu'))))
self.assertListEqual(token['upostag'].labels,
- ['VERB', 'ADP', 'NOUN', 'PUNCT'])
+ ['PRON', 'SCONJ', 'PROPN', 'VERB', 'ADP', 'PROPN', 'PUNCT'])
diff --git a/tests/data/data_readers/tl_trg-ud-test.conllu b/tests/data/data_readers/tl_trg-ud-test.conllu
deleted file mode 100644
index 4feec58e0ff99c3ee98739866d7e8ad8b083bba1..0000000000000000000000000000000000000000
--- a/tests/data/data_readers/tl_trg-ud-test.conllu
+++ /dev/null
@@ -1,1343 +0,0 @@
-# sent_id = schachter-otanes-60-0
-# text = Gumising ang bata.
-# text_en = The child awoke.
-1 Gumising gising VERB _ Aspect=Perf|Mood=Ind|Voice=Act 0 root _ Gloss=awakened
-2 ang ang ADP _ Case=Nom 3 case _ Gloss=the
-3 bata bata NOUN _ _ 1 nsubj _ Gloss=child|SpaceAfter=No
-4 . . PUNCT _ _ 1 punct _ _
-
-# sent_id = schachter-otanes-60-1
-# text = Ginising ng ingay ang bata.
-# text_en = A noise awakened the child.
-1 Ginising gising VERB _ Aspect=Perf|Mood=Ind|Voice=Pass 0 root _ Gloss=awakened
-2 ng ng ADP _ Case=Gen 3 case _ _
-3 ingay ingay NOUN _ _ 1 obj:agent _ Gloss=noise
-4 ang ang ADP _ Case=Nom 5 case _ Gloss=the
-5 bata bata NOUN _ _ 1 nsubj:pass _ Gloss=child|SpaceAfter=No
-6 . . PUNCT _ _ 1 punct _ _
-
-# sent_id = schachter-otanes-60-2
-# text = Sinulat ko ang liham.
-# text_en = I wrote the letter.
-1 Sinulat sulat VERB _ Aspect=Perf|Mood=Ind|Voice=Pass 0 root _ Gloss=written
-2 ko ako PRON _ Case=Gen|Number=Sing|Person=1|PronType=Prs 1 obj:agent _ Gloss=I
-3 ang ang ADP _ Case=Nom 4 case _ Gloss=the
-4 liham liham NOUN _ _ 1 nsubj:pass _ Gloss=letter|SpaceAfter=No
-5 . . PUNCT _ _ 1 punct _ _
-
-# sent_id = schachter-otanes-60-3
-# text = Sinulatan ko ang titser.
-# text_en = I wrote to the teacher.
-1 Sinulatan sulat VERB _ Aspect=Perf|Mood=Ind|Voice=Pass 0 root _ Gloss=written
-2 ko ako PRON _ Case=Gen|Number=Sing|Person=1|PronType=Prs 1 obj:agent _ Gloss=I
-3 ang ang ADP _ Case=Nom 4 case _ Gloss=the
-4 titser titser NOUN _ _ 1 nsubj:pass _ Gloss=teacher|SpaceAfter=No
-5 . . PUNCT _ _ 1 punct _ _
-
-# sent_id = schachter-otanes-61-2
-# text = Dumarating na ang bus.
-# text_en = The bus is coming now.
-1 Dumarating dating VERB _ Aspect=Imp|Mood=Ind|Voice=Act 0 root _ Gloss=coming
-2 na na ADV _ PronType=Dem 1 advmod _ Gloss=now
-3 ang ang ADP _ Case=Nom 4 case _ Gloss=the
-4 bus bus NOUN _ Foreign=Yes 1 nsubj _ Gloss=bus|SpaceAfter=No
-5 . . PUNCT _ _ 1 punct _ _
-
-# sent_id = schachter-otanes-61-3
-# text = Artista ang babae.
-# text_en = The woman is an actress.
-1 Artista artista NOUN _ _ 0 root _ Gloss=actress
-2 ang ang ADP _ Case=Nom 3 case _ Gloss=the
-3 babae babae NOUN _ _ 1 nsubj _ Gloss=woman|SpaceAfter=No
-4 . . PUNCT _ _ 1 punct _ _
-
-# sent_id = schachter-otanes-61-4
-# text = Maganda ang babae.
-# text_en = The woman is beautiful.
-1 Maganda ganda ADJ _ Degree=Pos 0 root _ Gloss=beautiful
-2 ang ang ADP _ Case=Nom 3 case _ Gloss=the
-3 babae babae NOUN _ _ 1 nsubj _ Gloss=woman|SpaceAfter=No
-4 . . PUNCT _ _ 1 punct _ _
-
-# sent_id = schachter-otanes-61-5
-# text = Yumaman ang babae.
-# text_en = The woman got rich.
-1 Yumaman yaman VERB _ Aspect=Perf|Mood=Ind|Voice=Act 0 root _ Gloss=got-rich
-2 ang ang ADP _ Case=Nom 3 case _ Gloss=the
-3 babae babae NOUN _ _ 1 nsubj _ Gloss=woman|SpaceAfter=No
-4 . . PUNCT _ _ 1 punct _ _
-
-# sent_id = schachter-otanes-62-0
-# text = Artista ang yumaman.
-# text_en = The one who got rich is an actress.
-1 Artista artista NOUN _ _ 0 root _ Gloss=actress
-2 ang ang ADP _ Case=Nom 3 case _ Gloss=the
-3 yumaman yaman VERB _ Aspect=Perf|Mood=Ind|Voice=Act 1 csubj _ Gloss=got-rich|SpaceAfter=No
-4 . . PUNCT _ _ 1 punct _ _
-
-# sent_id = schachter-otanes-62-1
-# text = Artista ang nagluto ng pagkain.
-# text_en = The one who cooked some food is an actress.
-1 Artista artista NOUN _ _ 3 nsubj _ Gloss=actress
-2 ang ang ADP _ Case=Nom 1 case _ Gloss=the
-3 nagluto luto VERB _ Aspect=Perf|Mood=Ind|Voice=Act 0 root _ Gloss=cooked
-4 ng ng ADP _ Case=Gen 5 case _ _
-5 pagkain pagkain NOUN _ _ 3 obj _ Gloss=food|SpaceAfter=No
-6 . . PUNCT _ _ 3 punct _ _
-
-# sent_id = schachter-otanes-64-0
-# text = Siya ang Amerikano.
-# text_en = He's the American.
-1 Siya siya PRON _ Case=Nom|Number=Sing|Person=3|PronType=Prs 0 root _ Gloss=he/she
-2 ang ang ADP _ Case=Nom 3 case _ Gloss=the
-3 Amerikano amerikano NOUN _ _ 1 nsubj _ Gloss=American|SpaceAfter=No
-4 . . PUNCT _ _ 1 punct _ _
-
-# sent_id = schachter-otanes-64-1
-# text = Iyan ang bahay.
-# text_en = That's the house.
-1 Iyan iyan PRON _ Case=Nom|Deixis=Med|Number=Sing|PronType=Dem 0 root _ Gloss=that
-2 ang ang ADP _ Case=Nom 3 case _ Gloss=the
-3 bahay bahay NOUN _ _ 1 obj _ Gloss=house|SpaceAfter=No
-4 . . PUNCT _ _ 1 punct _ _
-
-# sent_id = schachter-otanes-64-2
-# text = Si Juan ang bunso.
-# text_en = Juan's the youngest child.
-1 Si si ADP _ Case=Nom 2 case _ Gloss=the
-2 Juan Juan PROPN _ Gender=Masc 0 root _ Gloss=Juan
-3 ang ang ADP _ Case=Nom 4 case _ Gloss=the
-4 bunso bunso NOUN _ _ 2 nsubj _ Gloss=youngest|SpaceAfter=No
-5 . . PUNCT _ _ 2 punct _ _
-
-# sent_id = schachter-otanes-64-3
-# text = Isda ang bakalaw.
-# text_en = The cod is a fish.
-1 Isda isda NOUN _ _ 0 root _ Gloss=fish
-2 ang ang ADP _ Case=Nom 3 case _ Gloss=the
-3 bakalaw bakalaw NOUN _ _ 1 nsubj _ Gloss=cod|SpaceAfter=No
-4 . . PUNCT _ _ 1 punct _ _
-
-# sent_id = schachter-otanes-64-4
-# text = Isda ang pagkain niya.
-# text_en = His meal is some fish.
-1 Isda isda NOUN _ _ 0 root _ Gloss=fish
-2 ang ang ADP _ Case=Nom 3 case _ Gloss=the
-3 pagkain pagkain NOUN _ _ 1 nsubj _ Gloss=food
-4 niya siya PRON _ Case=Gen|Number=Sing|Person=3|PronType=Prs 3 nmod:poss _ Gloss=his/her|SpaceAfter=No
-5 . . PUNCT _ _ 1 punct _ _
-
-# sent_id = schachter-otanes-64-5
-# text = Isda ang paborito niya.
-# text_en = His favorite is fish.
-1 Isda isda NOUN _ _ 0 root _ Gloss=fish
-2 ang ang ADP _ Case=Nom 3 case _ Gloss=the
-3 paborito paborito NOUN _ _ 1 nsubj _ Gloss=favorite
-4 niya siya PRON _ Case=Gen|Number=Sing|Person=3|PronType=Prs 3 nmod:poss _ Gloss=his/her|SpaceAfter=No
-5 . . PUNCT _ _ 1 punct _ _
-
-# sent_id = schachter-otanes-64-6
-# text = Bato ang bahay.
-# text_en = The house is stone.
-1 Bato bato NOUN _ _ 0 root _ Gloss=stone
-2 ang ang ADP _ Case=Nom 3 case _ Gloss=the
-3 bahay bahay NOUN _ _ 1 nsubj _ Gloss=house|SpaceAfter=No
-4 . . PUNCT _ _ 1 punct _ _
-
-# sent_id = schachter-otanes-64-7
-# text = Bago ang bahay.
-# text_en = The house is new.
-1 Bago bago ADJ _ Degree=Pos 0 root _ Gloss=new
-2 ang ang ADP _ Case=Nom 3 case _ Gloss=the
-3 bahay bahay NOUN _ _ 1 nsubj _ Gloss=house|SpaceAfter=No
-4 . . PUNCT _ _ 1 punct _ _
-
-# sent_id = schachter-otanes-65-0
-# text = Bagong-bago ang bahay.
-# text_en = The house is very new.
-1 Bagong bago ADJ _ Degree=Pos|Link=Yes 3 compound:redup _ Gloss=new|SpaceAfter=No
-2 - - PUNCT _ _ 3 punct _ SpaceAfter=No
-3 bago bago ADJ _ Degree=Pos 0 root _ Gloss=new
-4 ang ang ADP _ Case=Nom 5 case _ Gloss=the
-5 bahay bahay NOUN _ _ 3 nsubj _ Gloss=house|SpaceAfter=No
-6 . . PUNCT _ _ 3 punct _ _
-
-# sent_id = schachter-otanes-65-2
-# text = Mabuti ang panahon.
-# text_en = The weather is good.
-1 Mabuti buti ADJ _ Degree=Pos 0 root _ Gloss=good
-2 ang ang ADP _ Case=Nom 3 case _ Gloss=the
-3 panahon panahon NOUN _ _ 1 nsubj _ Gloss=weather|SpaceAfter=No
-4 . . PUNCT _ _ 1 punct _ _
-
-# sent_id = schachter-otanes-65-3
-# text = Matamis ang kendi.
-# text_en = The candy is sweet.
-1 Matamis tamis ADJ _ Degree=Pos 0 root _ Gloss=sweet
-2 ang ang ADP _ Case=Nom 3 case _ Gloss=the
-3 kendi kendi NOUN _ _ 1 nsubj _ Gloss=candy|SpaceAfter=No
-4 . . PUNCT _ _ 1 punct _ _
-
-# sent_id = schachter-otanes-65-4
-# text = Pagod ang bata.
-# text_en = The child is tired.
-1 Pagod pagod ADJ _ Degree=Pos 0 root _ Gloss=tired
-2 ang ang ADP _ Case=Nom 3 case _ Gloss=the
-3 bata bata NOUN _ _ 1 nsubj _ Gloss=child|SpaceAfter=No
-4 . . PUNCT _ _ 1 punct _ _
-
-# sent_id = schachter-otanes-65-5
-# text = Nasa kusina ang mesa.
-# text_en = The table is in the kitchen.
-1 Nasa nasa ADP _ _ 2 case _ Gloss=in
-2 kusina kusina NOUN _ _ 0 root _ Gloss=kitchen
-3 ang ang ADP _ Case=Nom 4 case _ Gloss=the
-4 mesa mesa NOUN _ _ 2 nsubj _ Gloss=table|SpaceAfter=No
-5 . . PUNCT _ _ 2 punct _ _
-
-# sent_id = schachter-otanes-65-6
-# text = Para sa bata ang laruan.
-# text_en = The toy is for the child.
-1 Para para ADP _ _ 3 case _ Gloss=for
-2 sa sa ADP _ Case=Dat 3 case _ Gloss=to
-3 bata bata NOUN _ _ 0 root _ Gloss=child
-4 ang ang ADP _ Case=Nom 5 case _ Gloss=the
-5 laruan laruan NOUN _ _ 3 nsubj _ Gloss=toy|SpaceAfter=No
-6 . . PUNCT _ _ 3 punct _ _
-
-# sent_id = schachter-otanes-65-7
-# text = Tungkol sa giyera ang kuwento.
-# text_en = The story is about the war.
-1 Tungkol tungkol ADP _ _ 3 case _ Gloss=about
-2 sa sa ADP _ Case=Dat 3 case _ Gloss=to
-3 giyera giyera NOUN _ _ 0 root _ Gloss=war
-4 ang ang ADP _ Case=Nom 5 case _ Gloss=the
-5 kuwento kuwento NOUN _ _ 3 nsubj _ Gloss=story|SpaceAfter=No
-6 . . PUNCT _ _ 3 punct _ _
-
-# sent_id = schachter-otanes-65-8
-# text = May gulayan ang babae.
-# text_en = The woman has a vegetable garden.
-1 May may VERB _ Polarity=Pos 0 root _ Gloss=exist
-2 gulayan gulayan NOUN _ _ 1 obj _ Gloss=vegetable-garden
-3 ang ang ADP _ Case=Nom 4 case _ Gloss=the
-4 babae babae NOUN _ _ 1 nsubj _ Gloss=woman|SpaceAfter=No
-5 . . PUNCT _ _ 1 punct _ _
-
-# sent_id = schachter-otanes-65-9
-# text = Kailangan ko ang kuwalta.
-# text_en = I need the money.
-1 Kailangan kailangan VERB _ Aspect=Hab 0 root _ Gloss=necessary
-2 ko ako PRON _ Case=Gen|Number=Sing|Person=1|PronType=Prs 1 obj _ Gloss=I
-3 ang ang ADP _ Case=Nom 4 case _ Gloss=the
-4 kuwalta kuwalta NOUN _ _ 1 nsubj _ Gloss=money|SpaceAfter=No
-5 . . PUNCT _ _ 1 punct _ _
-
-# sent_id = schachter-otanes-65-10
-# text = Sa istudyante ang libro.
-# text_en = The book belongs to the student.
-1 Sa sa ADP _ Case=Dat 2 case _ Gloss=to
-2 istudyante istudyante NOUN _ _ 0 root _ Gloss=student
-3 ang ang ADP _ Case=Nom 4 case _ Gloss=the
-4 libro libro NOUN _ _ 2 nsubj _ Gloss=book|SpaceAfter=No
-5 . . PUNCT _ _ 2 punct _ _
-
-# sent_id = schachter-otanes-67-0
-# text = Nagluto ng pagkain ang nanay.
-# text_en = Mother cooked some food.
-1 Nagluto luto VERB _ Aspect=Perf|Mood=Ind|Voice=Act 0 root _ Gloss=cooked
-2 ng ng ADP _ Case=Gen 3 case _ _
-3 pagkain pagkain NOUN _ _ 1 obj _ Gloss=food
-4 ang ang ADP _ Case=Nom 5 case _ Gloss=the
-5 nanay nanay NOUN _ _ 1 nsubj _ Gloss=mother|SpaceAfter=No
-6 . . PUNCT _ _ 1 punct _ _
-
-# sent_id = schachter-otanes-67-1
-# text = Nagluto na ng pagkain ang nanay.
-# text_en = Mother has cooked some food.
-1 Nagluto luto VERB _ Aspect=Perf|Mood=Ind|Voice=Act 0 root _ Gloss=cooked
-2 na na ADV _ PronType=Dem 1 advmod _ Gloss=now
-3 ng ng ADP _ Case=Gen 4 case _ _
-4 pagkain pagkain NOUN _ _ 1 obj _ Gloss=food
-5 ang ang ADP _ Case=Nom 6 case _ Gloss=the
-6 nanay nanay NOUN _ _ 1 nsubj _ Gloss=mother|SpaceAfter=No
-7 . . PUNCT _ _ 1 punct _ _
-
-# sent_id = schachter-otanes-67-2
-# text = Nagluto na ng pagkain ang nanay noong dumating ako.
-# text_en = Mother had cooked some food when I arrived.
-1 Nagluto luto VERB _ Aspect=Perf|Mood=Ind|Voice=Act 0 root _ Gloss=cooked
-2 na na ADV _ PronType=Dem 1 advmod _ Gloss=now
-3 ng ng ADP _ Case=Gen 4 case _ _
-4 pagkain pagkain NOUN _ _ 1 obj _ Gloss=food
-5 ang ang ADP _ Case=Nom 6 case _ Gloss=the
-6 nanay nanay NOUN _ _ 1 nsubj _ Gloss=mother
-7 noong nang SCONJ _ _ 8 mark _ Gloss=when
-8 dumating dating VERB _ Aspect=Perf|Mood=Ind|Voice=Act 1 advcl _ Gloss=arrived
-9 ako ako PRON _ Case=Nom|Number=Sing|Person=1|PronType=Prs 8 nsubj _ Gloss=I|SpaceAfter=No
-10 . . PUNCT _ _ 1 punct _ _
-
-# sent_id = schachter-otanes-67-3
-# text = Nagluluto ng pagkain ang nanay araw-araw.
-# text_en = Mother is cooking some food everyday.
-1 Nagluluto luto VERB _ Aspect=Imp|Mood=Ind|Voice=Act 0 root _ Gloss=cooking
-2 ng ng ADP _ Case=Gen 3 case _ _
-3 pagkain pagkain NOUN _ _ 1 obj _ Gloss=food
-4 ang ang ADP _ Case=Nom 5 case _ Gloss=the
-5 nanay nanay NOUN _ _ 1 nsubj _ Gloss=mother
-6 araw araw NOUN _ _ 8 compound:redup _ Gloss=day|SpaceAfter=No
-7 - - PUNCT _ _ 8 punct _ SpaceAfter=No
-8 araw araw NOUN _ _ 1 obl _ Gloss=day|SpaceAfter=No
-9 . . PUNCT _ _ 1 punct _ _
-
-# sent_id = schachter-otanes-67-4
-# text = Nagluluto na ng pagkain ang nanay.
-# text_en = Mother is cooking some food now.
-1 Nagluluto luto VERB _ Aspect=Imp|Mood=Ind|Voice=Act 0 root _ Gloss=cooking
-2 na na ADV _ PronType=Dem 1 advmod _ Gloss=now
-3 ng ng ADP _ Case=Gen 4 case _ _
-4 pagkain pagkain NOUN _ _ 1 obj _ Gloss=food
-5 ang ang ADP _ Case=Nom 6 case _ Gloss=the
-6 nanay nanay NOUN _ _ 1 nsubj _ Gloss=mother|SpaceAfter=No
-7 . . PUNCT _ _ 1 punct _ _
-
-# sent_id = schachter-otanes-67-5
-# text = Nagluluto ng pagkain ang nanay noong dumating ako.
-# text_en = Mother was cooking some food when I arrived.
-1 Nagluluto luto VERB _ Aspect=Imp|Mood=Ind|Voice=Act 0 root _ Gloss=cooking
-2 ng ng ADP _ Case=Gen 3 case _ _
-3 pagkain pagkain NOUN _ _ 1 obj _ Gloss=food
-4 ang ang ADP _ Case=Nom 5 case _ Gloss=the
-5 nanay nanay NOUN _ _ 1 nsubj _ Gloss=mother
-6 noong nang SCONJ _ _ 7 mark _ Gloss=when
-7 dumating dating VERB _ Aspect=Perf|Mood=Ind|Voice=Act 1 advcl _ Gloss=arrived
-8 ako ako PRON _ Case=Nom|Number=Sing|Person=1|PronType=Prs 7 nsubj _ Gloss=I|SpaceAfter=No
-9 . . PUNCT _ _ 1 punct _ _
-
-# sent_id = schachter-otanes-67-6
-# text = Magluluto ng pagkain ang nanay bukas.
-# text_en = Mother will cook some food tomorrow.
-1 Magluluto luto VERB _ Aspect=Prosp|Mood=Ind|Voice=Act 0 root _ Gloss=will-cook
-2 ng ng ADP _ Case=Gen 3 case _ _
-3 pagkain pagkain NOUN _ _ 1 obj _ Gloss=food
-4 ang ang ADP _ Case=Nom 5 case _ Gloss=the
-5 nanay nanay NOUN _ _ 1 nsubj _ Gloss=mother
-6 bukas bukas ADV _ _ 1 advmod _ Gloss=tomorrow|SpaceAfter=No
-7 . . PUNCT _ _ 1 punct _ _
-
-# sent_id = schachter-otanes-67-7
-# text = Hindi pa nagluluto ng pagkain ang nanay.
-# text_en = Mother has not cooked any food yet.
-1 Hindi hindi PART _ Polarity=Neg 3 advmod _ Gloss=not
-2 pa pa ADV _ _ 3 advmod _ Gloss=yet
-3 nagluluto luto VERB _ Aspect=Imp|Mood=Ind|Voice=Act 0 root _ Gloss=cooking
-4 ng ng ADP _ Case=Gen 5 case _ _
-5 pagkain pagkain NOUN _ _ 3 obj _ Gloss=food
-6 ang ang ADP _ Case=Nom 7 case _ Gloss=the
-7 nanay nanay NOUN _ _ 3 nsubj _ Gloss=mother|SpaceAfter=No
-8 . . PUNCT _ _ 3 punct _ _
-
-# sent_id = schachter-otanes-69-1
-# text = Bumabasa ng diyaryo ang titser.
-# text_en = The teacher is reading a newspaper.
-1 Bumabasa basa VERB _ Aspect=Imp|Mood=Ind|Voice=Act 0 root _ Gloss=reading
-2 ng ng ADP _ Case=Gen 3 case _ _
-3 diyaryo diyaryo NOUN _ _ 1 obj _ Gloss=newspaper
-4 ang ang ADP _ Case=Nom 5 case _ Gloss=the
-5 titser titser NOUN _ _ 1 nsubj _ Gloss=teacher|SpaceAfter=No
-6 . . PUNCT _ _ 1 punct _ _
-
-# sent_id = schachter-otanes-69-2
-# text = Binabasa ng titser ang diyaryo.
-# text_en = The teacher is reading the newspaper.
-1 Binabasa basa VERB _ Aspect=Imp|Mood=Ind|Voice=Pass 0 root _ Gloss=being-read
-2 ng ng ADP _ Case=Gen 3 case _ _
-3 titser titser NOUN _ _ 1 obj:agent _ Gloss=teacher
-4 ang ang ADP _ Case=Nom 5 case _ Gloss=the
-5 diyaryo diyaryo NOUN _ _ 1 nsubj:pass _ Gloss=newspaper|SpaceAfter=No
-6 . . PUNCT _ _ 1 punct _ _
-
-# sent_id = schachter-otanes-69-3
-# text = Naghihilik ang lolo.
-# text_en = Grandfather is snoring.
-1 Naghihilik hilik VERB _ Aspect=Imp|Mood=Ind|Voice=Act 0 root _ Gloss=snoring
-2 ang ang ADP _ Case=Nom 3 case _ Gloss=the
-3 lolo lolo NOUN _ _ 1 nsubj _ Gloss=grandfather|SpaceAfter=No
-4 . . PUNCT _ _ 1 punct _ _
-
-# sent_id = schachter-otanes-69-4
-# text = Humihinga pa ang pasyente.
-# text_en = The patient is still breathing.
-1 Humihinga hinga VERB _ Aspect=Imp|Mood=Ind|Voice=Act 0 root _ Gloss=breathing
-2 pa pa ADV _ _ 1 advmod _ Gloss=still
-3 ang ang ADP _ Case=Nom 4 case _ Gloss=the
-4 pasyente pasyente NOUN _ _ 1 nsubj _ Gloss=patient|SpaceAfter=No
-5 . . PUNCT _ _ 1 punct _ _
-
-# sent_id = schachter-otanes-70-0
-# text = Nauuhaw ang sanggol.
-# text_en = The baby is getting thirsty.
-1 Nauuhaw uhaw VERB _ Aspect=Imp|Mood=Ind|Voice=Act 0 root _ Gloss=getting-thirsty
-2 ang ang ADP _ Case=Nom 3 case _ Gloss=the
-3 sanggol sanggol NOUN _ _ 1 nsubj _ Gloss=baby|SpaceAfter=No
-4 . . PUNCT _ _ 1 punct _ _
-
-# sent_id = schachter-otanes-70-1
-# text = Tumatanda ang aso.
-# text_en = The dog is growing old.
-1 Tumatanda magtanda VERB _ Aspect=Imp|Mood=Ind|Voice=Act 0 root _ Gloss=getting-older
-2 ang ang ADP _ Case=Nom 3 case _ Gloss=the
-3 aso aso NOUN _ _ 1 nsubj _ Gloss=dog|SpaceAfter=No
-4 . . PUNCT _ _ 1 punct _ _
-
-# sent_id = schachter-otanes-70-2
-# text = Ibinigay ng titser sa istudyante ang premyo.
-# text_en = The teacher gave the student the prize.
-1 Ibinigay bigay VERB _ Aspect=Perf|Mood=Ind|Voice=Pass 0 root _ Gloss=given
-2 ng ng ADP _ Case=Gen 3 case _ _
-3 titser titser NOUN _ _ 1 obj:agent _ Gloss=teacher
-4 sa sa ADP _ Case=Dat 5 case _ Gloss=to
-5 istudyante istudyante NOUN _ _ 1 obl _ Gloss=student
-6 ang ang ADP _ Case=Nom 7 case _ Gloss=the
-7 premyo premyo NOUN _ _ 1 nsubj:pass _ Gloss=prize|SpaceAfter=No
-8 . . PUNCT _ _ 1 punct _ _
-
-# sent_id = schachter-otanes-70-3
-# text = Binigyan ng titser ng premyo ang istudyante.
-# text_en = The teacher gave the student a prize.
-1 Binigyan bigay VERB _ Aspect=Perf|Mood=Ind|Voice=Lfoc 0 root _ Gloss=given
-2 ng ng ADP _ Case=Gen 3 case _ _
-3 titser titser NOUN _ _ 1 obj:agent _ Gloss=teacher
-4 ng ng ADP _ Case=Gen 3 case _ _
-5 premyo premyo NOUN _ _ 1 iobj _ Gloss=prize
-6 ang ang ADP _ Case=Nom 7 case _ Gloss=the
-7 istudyante istudyante NOUN _ _ 1 nsubj:lfoc _ Gloss=student|SpaceAfter=No
-8 . . PUNCT _ _ 1 punct _ _
-
-# sent_id = schachter-otanes-70-4
-# text = Binili ng mangingisda ang bangka.
-# text_en = The fisherman bought the boat.
-1 Binili bili VERB _ Aspect=Perf|Mood=Ind|Voice=Pass 0 root _ Gloss=bought
-2 ng ng ADP _ Case=Gen 3 case _ _
-3 mangingisda mangingisda NOUN _ _ 1 obj:agent _ Gloss=fisherman
-4 ang ang ADP _ Case=Nom 5 case _ Gloss=the
-5 bangka bangka NOUN _ _ 1 nsubj:pass _ Gloss=boat|SpaceAfter=No
-6 . . PUNCT _ _ 1 punct _ _
-
-# sent_id = schachter-otanes-70-5
-# text = Sinalpok ng alon ang bangka.
-# text_en = The wave struck the boat.
-1 Sinalpok salpok VERB _ Aspect=Perf|Mood=Ind|Voice=Lfoc 0 root _ Gloss=struck
-2 ng ng ADP _ Case=Gen 3 case _ _
-3 alon alon NOUN _ _ 1 obj:agent _ Gloss=wave
-4 ang ang ADP _ Case=Nom 5 case _ Gloss=the
-5 bangka bangka NOUN _ _ 1 nsubj:lfoc _ Gloss=boat|SpaceAfter=No
-6 . . PUNCT _ _ 1 punct _ _
-
-# sent_id = schachter-otanes-70-6
-# text = Bumili ng bangka ang mangingisda.
-# text_en = The fisherman bought a boat.
-1 Bumili bili VERB _ Aspect=Perf|Mood=Ind|Voice=Act 0 root _ Gloss=bought
-2 ng ng ADP _ Case=Gen 3 case _ _
-3 bangka bangka NOUN _ _ 1 obj _ Gloss=boat
-4 ang ang ADP _ Case=Nom 5 case _ Gloss=the
-5 mangingisda mangingisda NOUN _ _ 1 nsubj _ Gloss=fisherman|SpaceAfter=No
-6 . . PUNCT _ _ 1 punct _ _
-
-# sent_id = schachter-otanes-70-7
-# text = Sumalpok sa bangka ang alon.
-# text_en = The wave struck the boat.
-1 Sumalpok salpok VERB _ Aspect=Perf|Mood=Ind|Voice=Act 0 root _ Gloss=struck
-2 sa sa ADP _ Case=Dat 3 case _ Gloss=to
-3 bangka bangka NOUN _ _ 1 obl _ Gloss=boat
-4 ang ang ADP _ Case=Nom 5 case _ Gloss=the
-5 alon alon NOUN _ _ 1 nsubj _ Gloss=wave|SpaceAfter=No
-6 . . PUNCT _ _ 1 punct _ _
-
-# sent_id = schachter-otanes-71-0
-# text = Binalikan niya ang Maynila.
-# text_en = He returned to Manila.
-1 Binalikan balik VERB _ Aspect=Perf|Mood=Ind|Voice=Lfoc 0 root _ Gloss=returned
-2 niya siya PRON _ Case=Gen|Number=Sing|Person=3|PronType=Prs 1 obj:agent _ Gloss=he/she
-3 ang ang ADP _ Case=Nom 4 case _ Gloss=the
-4 Maynila Maynila PROPN _ _ 1 nsubj:lfoc _ Gloss=Manila|SpaceAfter=No
-5 . . PUNCT _ _ 1 punct _ _
-
-# sent_id = schachter-otanes-71-1
-# text = Tinakasan niya ang bilangguan.
-# text_en = He escaped from the prison.
-1 Tinakasan takas VERB _ Aspect=Perf|Mood=Ind|Voice=Lfoc 0 root _ Gloss=escaped
-2 niya siya PRON _ Case=Gen|Number=Sing|Person=3|PronType=Prs 1 obj:agent _ Gloss=he/she
-3 ang ang ADP _ Case=Nom 4 case _ Gloss=the
-4 bilangguan bilangguan NOUN _ _ 1 nsubj:lfoc _ Gloss=prison|SpaceAfter=No
-5 . . PUNCT _ _ 1 punct _ _
-
-# sent_id = schachter-otanes-95-10
-# text = Mansanas ito.
-# text_en = This is an apple.
-1 Mansanas mansanas NOUN _ _ 0 root _ Gloss=apple
-2 ito ito PRON _ Case=Nom|Deixis=Prox|Number=Sing|PronType=Dem 1 det _ Gloss=this|SpaceAfter=No
-3 . . PUNCT _ _ 1 punct _ _
-
-# sent_id = schachter-otanes-97-0
-# text = Biyudo ang maestro.
-# text_en = The teacher is a widower.
-1 Biyudo biyudo NOUN _ Gender=Masc 0 root _ Gloss=widower
-2 ang ang ADP _ Case=Nom 3 case _ Gloss=the
-3 maestro maestro NOUN _ Gender=Masc 1 nsubj _ Gloss=teacher|SpaceAfter=No
-4 . . PUNCT _ _ 1 punct _ _
-
-# sent_id = schachter-otanes-97-1
-# text = Biyuda ang maestra.
-# text_en = The teacher is a widow.
-1 Biyuda biyuda NOUN _ Gender=Fem 0 root _ Gloss=widow
-2 ang ang ADP _ Case=Nom 3 case _ Gloss=the
-3 maestra maestra NOUN _ Gender=Fem 1 nsubj _ Gloss=teacher|SpaceAfter=No
-4 . . PUNCT _ _ 1 punct _ _
-
-# sent_id = schachter-otanes-197-0
-# text = Komika si Linda.
-# text_en = Linda is funny.
-1 Komika komika ADJ _ Degree=Pos|Gender=Fem 0 root _ Gloss=funny
-2 si si ADP _ Case=Nom 3 case _ Gloss=the
-3 Linda Linda PROPN _ Gender=Fem 1 nsubj _ Gloss=Linda|SpaceAfter=No
-4 . . PUNCT _ _ 1 punct _ _
-
-# sent_id = devos-71-0
-# text = Nakita kita.
-# text_en = I saw you.
-1 Nakita kita VERB _ Aspect=Perf|Mood=Ind|Voice=Pass 0 root _ Gloss=seen
-2 kita ako PRON _ Case=Nom|Clusivity=In|Number=Dual|Person=1|PronType=Prs 1 nsubj:pass _ Gloss=I|SpaceAfter=No
-3 . . PUNCT _ _ 1 punct _ _
-
-# sent_id = schachter-otanes-73-0
-# text = Kinain ang pagkain.
-# text_en = The food was eaten.
-1 Kinain kain VERB _ Aspect=Perf|Mood=Ind|Voice=Act 0 root _ Gloss=ate
-2 ang ang ADP _ Case=Nom 3 case _ Gloss=the
-3 pagkain pagkain NOUN _ _ 1 nsubj _ Gloss=food|SpaceAfter=No
-4 . . PUNCT _ _ 1 punct _ _
-
-# sent_id = shopen-1.8
-# text = Mga guro sila.
-# gloss = PL teacher they
-# text_en = They are teachers
-1 Mga mga DET _ Number=Plur|PronType=Ind 2 det _ Gloss=PLUR
-2 guro guro NOUN _ _ 0 root _ Gloss=teacher
-3 sila sila PRON _ Case=Nom|Number=Plur|Person=3|PronType=Prs 2 nsubj _ Gloss=they|SpaceAfter=No
-4 . . PUNCT _ _ 2 punct _ Gloss=.
-
-# sent_id = shopen-1.12
-# text = Malapit sa babae ang bata.
-# gloss = near OBLIQ woman TOP child
-# text_en = The child is near the woman
-1 Malapit malapit ADJ _ Degree=Pos 0 root _ Gloss=near
-2 sa sa ADP _ Case=Dat 3 case _ Gloss=to
-3 babae babae NOUN _ _ 1 obl _ Gloss=woman
-4 ang ang ADP _ Case=Nom 5 case _ Gloss=the|MGloss=PIV
-5 bata bata NOUN _ _ 1 nsubj _ Gloss=child|SpaceAfter=No
-6 . . PUNCT _ _ 1 punct _ Gloss=.
-
-# sent_id = shopen-1.13
-# text = Malapit kay Maria si Juan.
-# gloss = near OBLIQ Maria TOP Juan
-# text_en = Juan is near Maria
-1 Malapit malapit ADJ _ Degree=Pos 0 root _ Gloss=near
-2 kay kay ADP _ Case=Dat 3 case _ Gloss=to
-3 Maria Maria PROPN _ Gender=Fem 1 obl _ Gloss=Maria
-4 si si ADP _ Case=Nom 5 case _ Gloss=the
-5 Juan Juan PROPN _ Gender=Masc 1 nsubj _ Gloss=Juan|SpaceAfter=No
-6 . . PUNCT _ _ 1 punct _ Gloss=.
-
-# sent_id = shopen-1.14
-# text = Malapit sa Maynila ang Pasay City.
-# gloss = near OBL Manila TOP Pasay City
-# text_en = Pasay City is near Manila
-1 Malapit malapit ADJ _ Degree=Pos 0 root _ Gloss=near
-2 sa sa ADP _ Case=Dat 3 case _ Gloss=to
-3 Maynila Maynila PROPN _ _ 1 obl _ Gloss=Manila
-4 ang ang ADP _ Case=Nom 5 case _ Gloss=the|MGloss=PIV
-5 Pasay Pasay PROPN _ _ 1 nsubj _ Gloss=Pasay
-6 City City PROPN _ _ 5 flat _ Gloss=City|SpaceAfter=No
-7 . . PUNCT _ _ 1 punct _ Gloss=.
-
-# sent_id = shopen-1.16a
-# text = Pinanood ko ang mga sumasayaw.
-# gloss = watch I TOP PL were.dancing
-# text_en = I watched the ones who were dancing
-# http://www.seasite.niu.edu/Tagalog/tagalog_verbs.htm
-1 Pinanood nood VERB _ Aspect=Perf|Mood=Ind|Voice=Pass 0 root _ Gloss=watch
-2 ko ako PRON _ Case=Gen|Number=Sing|Person=1|PronType=Prs 1 nsubj _ Gloss=me
-3 ang ang ADP _ Case=Nom 5 case _ Gloss=the|MGloss=PIV
-4 mga mga DET _ Number=Plur|PronType=Ind 5 det _ Gloss=PLUR
-5 sumasayaw sayaw VERB _ Aspect=Imp|Mood=Ind|Voice=Act 1 obj _ Gloss=were-dancing|SpaceAfter=No
-6 . . PUNCT _ _ 1 punct _ Gloss=.
-
-# sent_id = shopen-1.16b
-# text = Sumasayaw ang mga tao.
-# gloss = were.dancing TOP PL person
-# text_en = The people were dancing
-1 Sumasayaw sayaw VERB _ Aspect=Imp|Mood=Ind|Voice=Act 0 root _ Gloss=were-dancing
-2 ang ang ADP _ Case=Nom 4 case _ Gloss=the|MGloss=PIV
-3 mga mga DET _ Number=Plur|PronType=Ind 4 det _ Gloss=PLUR
-4 tao tao NOUN _ _ 1 nsubj _ Gloss=person|SpaceAfter=No
-5 . . PUNCT _ _ 1 punct _ Gloss=.
-
-# sent_id = shopen-1.24
-# text = Nagtatrabaho ang lalaki.
-# gloss = is.working TOP man
-# text_en = The man is working
-1 Nagtatrabaho trabaho VERB _ Aspect=Imp|Mood=Ind|Voice=Act 0 root _ Gloss=working|MGloss=is.working
-2 ang ang ADP _ Case=Nom 3 case _ Gloss=the|MGloss=PIV
-3 lalaki lalaki NOUN _ _ 1 nsubj _ Gloss=man|SpaceAfter=No
-4 . . PUNCT _ _ 1 punct _ Gloss=.
-
-# sent_id = shopen-1.25
-# text = Lalaki ang nagtatrabaho.
-# gloss = man TOP is.working
-# text_en = The one who is working is a man
-1 Lalaki lalaki NOUN _ _ 0 root _ Gloss=man
-2 ang ang ADP _ Case=Nom 3 case _ Gloss=the|MGloss=PIV
-3 nagtatrabaho trabaho VERB _ Aspect=Imp|Mood=Ind|Voice=Act 1 nsubj _ Gloss=working|MGloss=is.working|SpaceAfter=No
-4 . . PUNCT _ _ 1 punct _ Gloss=.
-
-# sent_id = shopen-1.55a
-# text = Hindi ko siya nakita.
-# gloss = not I(AG) him(TOP) saw
-# text_en = I didn't see him
-1 Hindi hindi PART _ Polarity=Neg 4 advmod _ Gloss=not
-2 ko ako PRON _ Case=Gen|Number=Sing|Person=1|PronType=Prs 4 nsubj _ Gloss=me
-3 siya siya PRON _ Case=Nom|Number=Sing|Person=3|PronType=Prs 4 obj _ Gloss=he
-4 nakita kita VERB _ Aspect=Perf|Mood=Ind|Voice=Pass 0 root _ Gloss=saw|SpaceAfter=No
-5 . . PUNCT _ _ 4 punct _ Gloss=.
-
-# sent_id = shopen-1.55b
-# text = Hindi nakita ni Pedro si Juan.
-# gloss = not saw AG Pedro TOP Juan
-# text_en = Pedro didn't see Juan
-1 Hindi hindi PART _ Polarity=Neg 2 advmod _ Gloss=not
-2 nakita kita VERB _ Aspect=Perf|Mood=Ind|Voice=Pass 0 root _ Gloss=saw
-3 ni ni ADP _ Case=Gen 4 case _ Gloss=DET
-4 Pedro Pedro PROPN _ Gender=Masc 2 nsubj _ Gloss=Pedro
-5 si si ADP _ Case=Nom 6 case _ Gloss=the
-6 Juan Juan PROPN _ Gender=Masc 2 obj _ Gloss=Juan|SpaceAfter=No
-7 . . PUNCT _ _ 2 punct _ Gloss=.
-
-# sent_id = shopen-1.63
-# text = Inahit ni John ang sarili niya.
-# gloss = shaved AG John TOP self his
-# text_en = John shaved himself
-1 Inahit ahit VERB _ Aspect=Perf|Mood=Ind|Voice=Pass 0 root _ Gloss=shaved
-2 ni ni ADP _ Case=Gen 3 case _ Gloss=DET
-3 John John PROPN _ Gender=Masc 1 nsubj _ Gloss=John
-4 ang ang ADP _ Case=Nom 5 case _ Gloss=the|MGloss=PIV
-5 sarili sarili PRON _ PronType=Prs|Reflex=Yes 1 obj _ Gloss=self
-6 niya siya PRON _ Case=Gen|Number=Sing|Person=3|PronType=Prs 5 nmod _ Gloss=him|SpaceAfter=No
-7 . . PUNCT _ _ 1 punct _ Gloss=.
-
-# sent_id = shopen-1.64
-# text = Inahit ni John mismo si Bill.
-# gloss = shaved AG John EMPH TOP Bill
-# text_en = John himself shaved Bill
-1 Inahit ahit VERB _ Aspect=Perf|Mood=Ind|Voice=Pass 0 root _ Gloss=shaved
-2 ni ni ADP _ Case=Gen 3 case _ Gloss=DET
-3 John John PROPN _ Gender=Masc 1 nsubj _ Gloss=John
-4 mismo mismo DET _ Gender=Masc|PronType=Emp 3 nmod _ Gloss=EMPH
-5 si si ADP _ Case=Nom 6 case _ Gloss=the
-6 Bill Bill PROPN _ Gender=Masc 1 obj _ Gloss=Bill|SpaceAfter=No
-7 . . PUNCT _ _ 1 punct _ Gloss=.
-
-# sent_id = shopen-1.84
-# text = Sino ang batang pumunta sa tindahan?
-# gloss = who TOP child went OBL store
-# text_en = Who is the child who went to the store?
-1 Sino sino PRON _ Case=Nom|PronType=Int 0 root _ Gloss=who
-2 ang ang ADP _ Case=Nom 3 case _ Gloss=the|MGloss=PIV
-3 batang bata NOUN _ Link=Yes 1 nsubj _ Gloss=child|MSeg=bata-ng|MGloss=child-LINK
-4 pumunta punta VERB _ Aspect=Perf|Mood=Ind|Voice=Act 3 acl:relcl _ Gloss=went
-5 sa sa ADP _ Case=Dat 6 case _ Gloss=to
-6 tindahan tindahan NOUN _ _ 4 obl _ Gloss=store|SpaceAfter=No
-7 ? ? PUNCT _ _ 1 punct _ Gloss=?
-
-# sent_id = shopen-1.89a
-# text = Umuulan ba?
-# gloss = is.raining Q
-# text_en = Is it raining?
-1 Umuulan ulan VERB _ Aspect=Imp|Mood=Ind|Voice=Act 0 root _ Gloss=is-raining
-2 ba ba PART _ PartType=Int 1 advmod _ Gloss=QUESTION|SpaceAfter=No
-3 ? ? PUNCT _ _ 1 punct _ Gloss=?
-
-# sent_id = shopen-1.89b
-# text = Oo.
-# gloss = yes
-# text_en = Yes
-1 Oo oo INTJ _ Polarity=Pos 0 root _ Gloss=yes|SpaceAfter=No
-2 . . PUNCT _ _ 1 punct _ Gloss=.
-
-# sent_id = shopen-1.89c
-# text = Hindi.
-# gloss = no
-# text_en = No
-1 Hindi hindi INTJ _ Polarity=Pos 0 root _ Gloss=no|SpaceAfter=No
-2 . . PUNCT _ _ 1 punct _ Gloss=.
-
-# sent_id = shopen-1.90a
-# text = Mayroon bang pagkain?
-# gloss = EXIST Q-LINK food
-# text_en = Is there any food?
-1 Mayroon mayroon VERB _ Polarity=Pos 0 root _ Gloss=exists
-2 bang ba PART _ Link=Yes|PartType=Int 1 advmod _ Gloss=QUESTION|MSeg=ba-ng|MGloss=QUESTION-LINK
-3 pagkain pagkain NOUN _ _ 1 nsubj _ Gloss=food|SpaceAfter=No
-4 ? ? PUNCT _ _ 1 punct _ Gloss=?
-
-# sent_id = shopen-1.90b
-# text = Mayroon.
-# gloss = EXIST
-# text_en = Yes (answer to existential questions)
-1 Mayroon mayroon VERB _ Polarity=Pos 0 root _ Gloss=exists|SpaceAfter=No
-2 . . PUNCT _ _ 1 punct _ Gloss=.
-
-# sent_id = shopen-1.90c
-# text = Wala.
-# gloss = NEG-EXIST
-# text_en = No (answer to existential questions)
-1 Wala wala VERB _ Polarity=Neg 0 root _ Gloss=does-not-exist|SpaceAfter=No
-2 . . PUNCT _ _ 1 punct _ Gloss=.
-
-# sent_id = shopen-1.92
-# text = Umuulan, ano?
-# gloss = is.raining CONFIRMATION TAG
-# text_en = It's raining, isn't it?
-1 Umuulan ulan VERB _ Aspect=Imp|Mood=Ind|Voice=Act 0 root _ Gloss=is-raining|SpaceAfter=No
-2 , , PUNCT _ _ 3 punct _ Gloss=,
-3 ano ano PART _ PartType=Int 1 advmod _ Gloss=CONFIRMATION-TAG|SpaceAfter=No
-4 ? ? PUNCT _ _ 1 punct _ Gloss=?
-
-# sent_id = shopen-1.98a
-# text = Napakaano nila?
-# gloss = very.what they
-# text_en = What are they very much like?
-# "Napaka-" is an intensifying prefix meaning "very". For example, "napakabuti" means "so very good".
-# We consider "napakaano" an adjective derived from the interrogative pronoun "ano" (what).
-1 Napakaano ano ADJ _ Degree=Pos|PronType=Int 0 root _ Gloss=very-much-like|MSeg=napaka-ano|MGloss=very-what
-2 nila sila PRON _ Case=Gen|Number=Plur|Person=3|PronType=Prs 1 nsubj _ Gloss=them|SpaceAfter=No
-3 ? ? PUNCT _ _ 1 punct _ Gloss=?
-
-# sent_id = shopen-1.98b
-# text = Napakataas nila.
-# gloss = very.tall they
-# text_en = They are very tall
-1 Napakataas taas ADJ _ Degree=Pos 0 root _ Gloss=very-tall|MSeg=napaka-taas|MGloss=very-tall
-2 nila sila PRON _ Case=Gen|Number=Plur|Person=3|PronType=Prs 1 nsubj _ Gloss=them|SpaceAfter=No
-3 . . PUNCT _ _ 1 punct _ Gloss=.
-
-# sent_id = shopen-1.98c
-# text = Nagano ka?
-# gloss = (PERF.ACTIVE)what you
-# text_en = What did you do?
-# We consider "ano" a verb, resulting from a conversion from the pronoun "ano" (what), acquiring verbal morphology.
-1 Nagano ano VERB _ Aspect=Perf|Mood=Ind|PronType=Int|Voice=Act 0 root _ Gloss=what-did|MSeg=nag-ano|MGloss=PERF+ACTIVE-what
-2 ka ikaw PRON _ Case=Nom|Number=Sing|Person=2|PronType=Prs 1 nsubj _ Gloss=you|SpaceAfter=No
-3 ? ? PUNCT _ _ 1 punct _ Gloss=?
-
-# sent_id = shopen-1.98d
-# text = Nagsalita ka.
-# gloss = (PERF.ACTIVE)speak you
-# text_en = You spoke
-1 Nagsalita salita VERB _ Aspect=Perf|Mood=Ind|Voice=Act 0 root _ Gloss=spoke|MSeg=nag-salita|MGloss=PERF+ACTIVE-speak
-2 ka ikaw PRON _ Case=Nom|Number=Sing|Person=2|PronType=Prs 1 nsubj _ Gloss=you|SpaceAfter=No
-3 . . PUNCT _ _ 1 punct _ Gloss=.
-
-# sent_id = shopen-1.98e
-# text = Naano ka?
-# gloss = (PERF.INVOL)what you
-# text_en = What happened to you?
-# We consider "ano" a verb, resulting from a conversion from the pronoun "ano" (what), acquiring verbal morphology.
-1 Naano ano VERB _ Aspect=Perf|Mood=Ind|PronType=Int|Voice=Pass 0 root _ Gloss=what-happened|MSeg=na-ano|MGloss=PERF+INVOL-what
-2 ka ikaw PRON _ Case=Nom|Number=Sing|Person=2|PronType=Prs 1 nsubj _ Gloss=you|SpaceAfter=No
-3 ? ? PUNCT _ _ 1 punct _ Gloss=?
-
-# sent_id = shopen-1.98f
-# text = Natalisod ka.
-# gloss = (PERF.INVOL)trip you
-# text_en = You tripped
-1 Natalisod tisod VERB _ Aspect=Perf|Mood=Ind|Voice=Pass 0 root _ Gloss=tripped|MSeg=na-talisod|MGloss=PERF+INVOL-trip
-2 ka ikaw PRON _ Case=Nom|Number=Sing|Person=2|PronType=Prs 1 nsubj _ Gloss=you|SpaceAfter=No
-3 . . PUNCT _ _ 1 punct _ Gloss=.
-
-# sent_id = shopen-1.100
-# text = Ipinansulat ni John ng liham kay Mary ang makinilya.
-# gloss = wrote.with AG John OBJ letter IO Mary TOP typewriter
-# text_en = John wrote Mary a letter on the typewriter
-1 Ipinansulat sulat VERB _ Aspect=Perf|Mood=Ind|Voice=Ifoc 0 root _ Gloss=wrote-with
-2 ni ni ADP _ Case=Gen 3 case _ Gloss=DET
-3 John John PROPN _ Gender=Masc 1 obj:agent _ Gloss=John
-4 ng ng ADP _ Case=Gen 5 case _ Gloss=DET
-5 liham liham NOUN _ _ 1 obj _ Gloss=letter
-6 kay kay ADP _ Case=Dat 7 case _ Gloss=to
-7 Mary Mary PROPN _ Gender=Fem 1 obl _ Gloss=Mary
-8 ang ang ADP _ Case=Nom 9 case _ Gloss=the|MGloss=PIV
-9 makinilya makinilya NOUN _ _ 1 nsubj:ifoc _ Gloss=typewriter|SpaceAfter=No
-10 . . PUNCT _ _ 1 punct _ Gloss=.
-
-# sent_id = shopen-1.109
-# text = Nasaan ang mga pinggan?
-# gloss = where TOP PL dish
-# text_en = Where are the dishes?
-1 Nasaan nasaan ADV _ PronType=Int 0 root _ Gloss=where
-2 ang ang ADP _ Case=Nom 4 case _ Gloss=the|MGloss=PIV
-3 mga mga DET _ Number=Plur|PronType=Ind 4 det _ Gloss=PLUR
-4 pinggan pinggan NOUN _ _ 1 nsubj _ Gloss=dish|SpaceAfter=No
-5 ? ? PUNCT _ _ 1 punct _ Gloss=?
-
-# sent_id = shopen-1.141
-# text = Itinanong ko kung nasaan sila.
-# gloss = asked I COMP where they
-# text_en = I asked where they were
-1 Itinanong tanong VERB _ Aspect=Perf|Mood=Ind|Voice=Pass 0 root _ Gloss=asked
-2 ko ako PRON _ Case=Gen|Number=Sing|Person=1|PronType=Prs 1 nsubj _ Gloss=me
-3 kung kung SCONJ _ _ 4 mark _ Gloss=that
-4 nasaan nasaan ADV _ PronType=Int 1 ccomp _ Gloss=where
-5 sila sila PRON _ Case=Nom|Number=Plur|Person=3|PronType=Prs 4 nsubj _ Gloss=they|SpaceAfter=No
-6 . . PUNCT _ _ 1 punct _ Gloss=.
-
-# sent_id = shopen-1.164a
-# text = Darating daw si Pedro bukas.
-# gloss = will.arrive they.say TOP Pedro tomorrow
-# text_en = They say Pedro will arrive tomorrow
-1 Darating dating VERB _ Aspect=Prog|Mood=Ind|Voice=Act 0 root _ Gloss=will-arrive
-2 daw daw PART _ PartType=Nfh 1 advmod _ Gloss=they-say
-3 si si ADP _ Case=Nom 4 case _ Gloss=the
-4 Pedro Pedro PROPN _ Gender=Masc 1 nsubj _ Gloss=Pedro
-5 bukas bukas ADV _ _ 1 advmod _ Gloss=tomorrow|SpaceAfter=No
-6 . . PUNCT _ _ 1 punct _ Gloss=.
-
-# sent_id = shopen-1.164b
-# text = Hindi daw darating si Pedro bukas.
-# gloss = NEG they.say will.arrive TOP Pedro tomorrow
-# text_en = They say Pedro won't arrive tomorrow
-1 Hindi hindi PART _ Polarity=Neg 3 advmod _ Gloss=not
-2 daw daw PART _ PartType=Nfh 3 advmod _ Gloss=they-say
-3 darating dating VERB _ Aspect=Prog|Mood=Ind|Voice=Act 0 root _ Gloss=will-arrive
-4 si si ADP _ Case=Nom 5 case _ Gloss=the
-5 Pedro Pedro PROPN _ Gender=Masc 3 nsubj _ Gloss=Pedro
-6 bukas bukas ADV _ _ 3 advmod _ Gloss=tomorrow|SpaceAfter=No
-7 . . PUNCT _ _ 3 punct _ Gloss=.
-
-# sent_id = shopen-1.164c
-# text = Bakit daw hindi darating si Pedro bukas?
-# gloss = why they.say NEG will.arrive TOP Pedro tomorrow
-# text_en = Why do they say Pedro won't arrive tomorrow?
-1 Bakit bakit ADV _ PronType=Int 4 advmod _ Gloss=why
-2 daw daw PART _ PartType=Nfh 4 advmod _ Gloss=they-say
-3 hindi hindi PART _ Polarity=Neg 4 advmod _ Gloss=not
-4 darating dating VERB _ Aspect=Prog|Mood=Ind|Voice=Act 0 root _ Gloss=will-arrive
-5 si si ADP _ Case=Nom 6 case _ Gloss=the
-6 Pedro Pedro PROPN _ Gender=Masc 4 nsubj _ Gloss=Pedro
-7 bukas bukas ADV _ _ 4 advmod _ Gloss=tomorrow|SpaceAfter=No
-8 ? ? PUNCT _ _ 4 punct _ Gloss=?
-
-# sent_id = shopen-1.167a
-# text = Nagtatrabaho ka na ba daw roon?
-# gloss = are.working you now Q they.say there
-# text_en = Do they say you are working there now?
-1 Nagtatrabaho trabaho VERB _ Aspect=Imp|Mood=Ind|Voice=Act 0 root _ Gloss=working|MGloss=are.working
-2 ka ikaw PRON _ Case=Nom|Number=Sing|Person=2|PronType=Prs 1 nsubj _ Gloss=you
-3 na na ADV _ PronType=Dem 1 advmod _ Gloss=now
-4 ba ba PART _ PartType=Int 1 advmod _ Gloss=QUESTION
-5 daw daw PART _ PartType=Nfh 1 advmod _ Gloss=they-say
-6 roon roon ADV _ Deixis=Remt|PronType=Dem 1 advmod _ Gloss=there|SpaceAfter=No
-7 ? ? PUNCT _ _ 1 punct _ Gloss=?
-
-# sent_id = shopen-1.167b
-# text = Nagtatrabaho ka na daw ba roon?
-# gloss = are.working you now they.say Q there
-# text_en = Do they say you are working there now?
-1 Nagtatrabaho trabaho VERB _ Aspect=Imp|Mood=Ind|Voice=Act 0 root _ Gloss=working|MGloss=are.working
-2 ka ikaw PRON _ Case=Nom|Number=Sing|Person=2|PronType=Prs 1 nsubj _ Gloss=you
-3 na na ADV _ PronType=Dem 1 advmod _ Gloss=now
-4 daw daw PART _ PartType=Nfh 1 advmod _ Gloss=they-say
-5 ba ba PART _ PartType=Int 1 advmod _ Gloss=QUESTION
-6 roon roon ADV _ Deixis=Remt|PronType=Dem 1 advmod _ Gloss=there|SpaceAfter=No
-7 ? ? PUNCT _ _ 1 punct _ Gloss=?
-
-# sent_id = shopen-1.168
-# text = Hindi pa man lamang tuloy siya nakakapagalmusal.
-# gloss = NEG yet even just as.a.result he can.have.breakfast
-# text_en = As a result, he hasn't even been able to have breakfast yet
-1 Hindi hindi PART _ Polarity=Neg 7 advmod _ Gloss=not
-2 pa pa ADV _ _ 7 advmod _ Gloss=yet
-3 man man ADV _ _ 7 advmod _ Gloss=even
-4 lamang lamang ADV _ _ 7 advmod _ Gloss=just
-5 tuloy tuloy ADV _ _ 7 advmod _ Gloss=as-a-result
-6 siya siya PRON _ Case=Nom|Number=Sing|Person=3|PronType=Prs 7 nsubj _ Gloss=he
-7 nakakapagalmusal almusal VERB _ Aspect=Imp|Mood=Pot|Voice=Act 0 root _ Gloss=can-have-breakfast|SpaceAfter=No
-8 . . PUNCT _ _ 7 punct _ Gloss=.
-
-# sent_id = shopen-1.183a
-# text = Mayroong libro sa mesa.
-# gloss = EXIST/POSS-LINK book on table
-# text_en = There is a book on the table
-1 Mayroong mayroon VERB _ Link=Yes|Polarity=Pos 0 root _ Gloss=there-is|MSeg=mayroon-g|MGloss=exists-POSSESSIVE
-2 libro libro NOUN _ _ 1 obj _ Gloss=book
-3 sa sa ADP _ Case=Dat 4 case _ Gloss=to
-4 mesa mesa NOUN _ _ 1 obl _ Gloss=table|SpaceAfter=No
-5 . . PUNCT _ _ 1 punct _ Gloss=.
-
-# sent_id = shopen-1.183b
-# text = Walang libro sa mesa.
-# gloss = EXIST/POSS(NEG)-LINK book on table
-# text_en = There isn't a book on the table
-1 Walang wala VERB _ Link=Yes|Polarity=Neg 0 root _ Gloss=there-is-not|MSeg=wala-ng|MGloss=does+not+exist-POSSESSIVE
-2 libro libro NOUN _ _ 1 obj _ Gloss=book
-3 sa sa ADP _ Case=Dat 4 case _ Gloss=to
-4 mesa mesa NOUN _ _ 1 obl _ Gloss=table|SpaceAfter=No
-5 . . PUNCT _ _ 1 punct _ Gloss=.
-
-# sent_id = shopen-1.183c
-# text = Mayroong libro ang bata.
-# gloss = EXIST/POSS-LINK book TOP child
-# text_en = The child has a book
-1 Mayroong mayroon VERB _ Link=Yes|Polarity=Pos 0 root _ Gloss=there-is|MSeg=mayroon-g|MGloss=exists-POSSESSIVE
-2 libro libro NOUN _ _ 1 obj _ Gloss=book
-3 ang ang ADP _ Case=Nom 4 case _ Gloss=the|MGloss=PIV
-4 bata bata NOUN _ _ 1 nsubj _ Gloss=child|SpaceAfter=No
-5 . . PUNCT _ _ 1 punct _ Gloss=.
-
-# sent_id = shopen-1.183d
-# text = Walang libro ang bata.
-# gloss = EXIST/POSS(NEG)-LINK book TOP child
-# text_en = The child doesn't have a book
-1 Walang wala VERB _ Link=Yes|Polarity=Neg 0 root _ Gloss=there-is-not|MSeg=wala-ng|MGloss=does+not+exist-POSSESSIVE
-2 libro libro NOUN _ _ 1 obj _ Gloss=book
-3 ang ang ADP _ Case=Nom 4 case _ Gloss=the|MGloss=PIV
-4 bata bata NOUN _ _ 1 nsubj _ Gloss=child|SpaceAfter=No
-5 . . PUNCT _ _ 1 punct _ Gloss=.
-
-# sent_id = shopen-1.185a
-# text = Mabuti ba ang ani?
-# The actual example in Shopen (2007) is "Mabuti a ang ani?". According to Ann Tan, "a" is a typo and it should be "ba".
-# gloss = good Q TOP harvest
-# text_en = Is the harvest good?
-1 Mabuti mabuti ADJ _ Degree=Pos 0 root _ Gloss=good
-2 ba ba PART _ PartType=Int 1 advmod _ Gloss=QUESTION
-3 ang ang ADP _ Case=Nom 4 case _ Gloss=the|MGloss=PIV
-4 ani ani NOUN _ _ 1 nsubj _ Gloss=harvest|SpaceAfter=No
-5 ? ? PUNCT _ _ 1 punct _ Gloss=?
-
-# sent_id = shopen-1.185b
-# text = Mabuti kaya ang ani?
-# gloss = good Q.SPECULATIVE TOP harvest
-# text_en = Do you suppose the harvest will be good?
-1 Mabuti mabuti ADJ _ Degree=Pos 0 root _ Gloss=good
-2 kaya kaya PART _ PartType=Int 1 advmod _ Gloss=QUESTION-SPECULATIVE
-3 ang ang ADP _ Case=Nom 4 case _ Gloss=the|MGloss=PIV
-4 ani ani NOUN _ _ 1 nsubj _ Gloss=harvest|SpaceAfter=No
-5 ? ? PUNCT _ _ 1 punct _ Gloss=?
-
-# sent_id = shopen-1.185c
-# text = Mabuti sana ang ani.
-# gloss = good WISH TOP harvest
-# text_en = I hope the harvest is good
-1 Mabuti mabuti ADJ _ Degree=Pos 0 root _ Gloss=good
-2 sana sana PART _ PartType=Des 1 advmod _ Gloss=WISH
-3 ang ang ADP _ Case=Nom 4 case _ Gloss=the|MGloss=PIV
-4 ani ani NOUN _ _ 1 nsubj _ Gloss=harvest|SpaceAfter=No
-5 . . PUNCT _ _ 1 punct _ Gloss=.
-
-# sent_id = shopen-1.186a
-# text = Huwag kayong umalis.
-# gloss = NEG you-LINK leave
-# text_en = Don't leave
-1 Huwag huwag AUX _ Mood=Imp|Polarity=Neg 3 aux _ Gloss=do-not
-2 kayong kayo PRON _ Case=Nom|Link=Yes|Number=Plur|Person=2|PronType=Prs 3 nsubj _ Gloss=you|MSeg=kayo-ng|MGloss=you-LINK
-3 umalis alis VERB _ Aspect=Perf|Mood=Ind|Voice=Act 0 root _ Gloss=leave|SpaceAfter=No
-4 . . PUNCT _ _ 3 punct _ Gloss=.
-
-# sent_id = shopen-1.186b
-# text = Huwag siyang pumarito.
-# gloss = NEG he-LINK come.here
-# text_en = He shouldn't come here
-1 Huwag huwag AUX _ Mood=Imp|Polarity=Neg 3 aux _ Gloss=do-not
-2 siyang siya PRON _ Case=Nom|Link=Yes|Number=Sing|Person=3|PronType=Prs 3 nsubj _ Gloss=he|MSeg=siya-ng|MGloss=he-LINK
-3 pumarito parito VERB _ Aspect=Perf|Mood=Ind|Voice=Act 0 root _ Gloss=come-here|SpaceAfter=No
-4 . . PUNCT _ _ 3 punct _ Gloss=.
-
-# sent_id = shopen-3.111a
-# text = Magaalis ang babae ng bigas sa sako para sa bata.
-# gloss = AP-FUT-take.out PIV woman OBJ rice DIR sack for BEN child
-# text_en = The woman will take some rice out of a/the sack for a/the child
-# AP = actor pivot; PIV = pivot marker
-# http://www.seasite.niu.edu/Tagalog/tagalog_verbs.htm
-1 Magaalis alis VERB _ Aspect=Prog|Mood=Ind|Voice=Act 0 root _ Gloss=will-take-out|MSeg=mag-a-alis|MGloss=AP-FUT-take.out
-2 ang ang ADP _ Case=Nom 3 case _ Gloss=the|MGloss=PIV
-3 babae babae NOUN _ _ 1 nsubj _ Gloss=woman
-4 ng ng ADP _ Case=Gen 5 case _ Gloss=DET
-5 bigas bigas NOUN _ _ 1 obj _ Gloss=rice
-6 sa sa ADP _ Case=Dat 7 case _ Gloss=to
-7 sako sako NOUN _ _ 1 obl _ Gloss=sack
-8 para para ADP _ _ 10 case _ Gloss=for
-9 sa sa ADP _ Case=Dat 10 case _ Gloss=to
-10 bata bata NOUN _ _ 1 obl _ Gloss=child|SpaceAfter=No
-11 . . PUNCT _ _ 1 punct _ Gloss=.
-
-# sent_id = shopen-3.111b
-# text = Aalisin ng babae ang bigas sa sako para sa bata.
-# gloss = FUT-take.out-OP ACT woman PIV rice DIR sack for BEN child
-# text_en = A/the woman will take the rice out of a/the sack for a/the child
-# OP = object pivot; PIV = pivot marker
-1 Aalisin alis VERB _ Aspect=Prog|Mood=Ind|Voice=Pass 0 root _ Gloss=will-take-out|MSeg=a-alis-in|MGloss=FUT-take.out-OP
-2 ng ng ADP _ Case=Gen 3 case _ Gloss=DET
-3 babae babae NOUN _ _ 1 obj:agent _ Gloss=woman
-4 ang ang ADP _ Case=Nom 5 case _ Gloss=the|MGloss=PIV
-5 bigas bigas NOUN _ _ 1 nsubj:pass _ Gloss=rice
-6 sa sa ADP _ Case=Dat 7 case _ Gloss=to
-7 sako sako NOUN _ _ 1 obl _ Gloss=sack
-8 para para ADP _ _ 10 case _ Gloss=for
-9 sa sa ADP _ Case=Dat 10 case _ Gloss=to
-10 bata bata NOUN _ _ 1 obl _ Gloss=child|SpaceAfter=No
-11 . . PUNCT _ _ 1 punct _ Gloss=.
-
-# sent_id = shopen-3.111c
-# text = Aalisan ng babae ng bigas ang sako para sa bata.
-# gloss = FUT-take.out-DP ACT woman OBJ rice PIV sack BEN child
-# text_en = A/the woman will take some rice out of the sack for a/the child
-# DP = directional pivot; PIV = pivot marker
-1 Aalisan alis VERB _ Aspect=Prog|Mood=Ind|Voice=Lfoc 0 root _ Gloss=will-take-out|MSeg=a-alis-an|MGloss=FUT-take.out-DP
-2 ng ng ADP _ Case=Gen 3 case _ Gloss=DET
-3 babae babae NOUN _ _ 1 obj:agent _ Gloss=woman
-4 ng ng ADP _ Case=Gen 5 case _ Gloss=DET
-5 bigas bigas NOUN _ _ 1 iobj:patient _ Gloss=rice
-6 ang ang ADP _ Case=Nom 7 case _ Gloss=the|MGloss=PIV
-7 sako sako NOUN _ _ 1 nsubj:lfoc _ Gloss=sack
-8 para para ADP _ _ 10 case _ Gloss=for
-9 sa sa ADP _ Case=Dat 10 case _ Gloss=to
-10 bata bata NOUN _ _ 1 obl _ Gloss=child|SpaceAfter=No
-11 . . PUNCT _ _ 1 punct _ Gloss=.
-
-# sent_id = shopen-3.111d
-# text = Ipagaalis ng babae ng bigas sa sako ang bata.
-# gloss = BP-FUT-take.out ACT woman OBJ rice DIR sack PIV child
-# text_en = A/the woman will take some rice out of a/the sack for the child
-# BP = benefactive pivot; PIV = pivot marker
-1 Ipagaalis alis VERB _ Aspect=Prog|Mood=Ind|Voice=Bfoc 0 root _ Gloss=will-take-out|MSeg=Ipag-a-alis|MGloss=BP-FUT-take.out
-2 ng ng ADP _ Case=Gen 3 case _ Gloss=DET
-3 babae babae NOUN _ _ 1 obj:agent _ Gloss=woman
-4 ng ng ADP _ Case=Gen 5 case _ Gloss=DET
-5 bigas bigas NOUN _ _ 1 iobj:patient _ Gloss=rice
-6 sa sa ADP _ Case=Dat 7 case _ Gloss=to
-7 sako sako NOUN _ _ 1 obl _ Gloss=sack
-8 ang ang ADP _ Case=Nom 9 case _ Gloss=the|MGloss=PIV
-9 bata bata NOUN _ _ 1 nsubj:bfoc _ Gloss=child|SpaceAfter=No
-10 . . PUNCT _ _ 1 punct _ Gloss=.
-
-# sent_id = shopen-3.112a
-# text = Matalino ang lalaking bumasa ng diyaryo.
-# gloss = intelligent PIV man-LINK [AP]-read OBJ newspaper
-# text_en = The man who read a newspaper is intelligent
-1 Matalino matalino ADJ _ Degree=Pos 0 root _ Gloss=intelligent
-2 ang ang ADP _ Case=Nom 3 case _ Gloss=the|MGloss=PIV
-3 lalaking lalaki NOUN _ Link=Yes 1 nsubj _ Gloss=man|MSeg=lalaki-ng|man-LINK
-4 bumasa basa VERB _ Aspect=Perf|Mood=Ind|Voice=Act 3 acl:relcl _ Gloss=read|MSeg=b[um]asa|MGloss=[AP]-read
-5 ng ng ADP _ Case=Gen 6 case _ Gloss=DET
-6 diyaryo diyaryo NOUN _ _ 4 obj _ Gloss=newspaper|SpaceAfter=No
-7 . . PUNCT _ _ 1 punct _ Gloss=.
-
-# sent_id = shopen-3.112b
-# text = Interesante ang diyaryong binasa ng lalaki.
-# gloss = interesting PIV newspaper-LINK [PERF]-read-OP ACT man
-# text_en = The newspaper that the man read is interesting
-1 Interesante interesante ADJ _ Degree=Pos 0 root _ Gloss=interesting
-2 ang ang ADP _ Case=Nom 3 case _ Gloss=the|MGloss=PIV
-3 diyaryong diyaryo NOUN _ Link=Yes 1 nsubj _ Gloss=newspaper|MSeg=diyaryo-ng|MGloss=newspaper-LINK
-4 binasa basa VERB _ Aspect=Perf|Mood=Ind|Voice=Pass 3 acl:relcl _ Gloss=be-read|MSeg=b[in]asa-0|MGloss=[PERF]-read-OP
-5 ng ng ADP _ Case=Gen 6 case _ Gloss=DET
-6 lalaki lalaki NOUN _ _ 4 obj _ Gloss=man|SpaceAfter=No
-7 . . PUNCT _ _ 1 punct _ Gloss=.
-
-# sent_id = shopen-3.114a
-# text = Susulat lahat ang mga bata ng mga liham.
-# source = Schachter and Otanes, 1972:147-8
-# gloss = AP-FUT-write all PIV PL child OBJ PL letter
-# text_en = All the children will write letters
-1 Susulat sulat VERB _ Aspect=Prog|Mood=Ind|Voice=Act 0 root _ Gloss=will-write|MSeg=0-su-sulat|MGloss=AP-FUT-write
-2 lahat lahat DET _ PronType=Tot 5 det _ Gloss=all
-3 ang ang ADP _ Case=Nom 5 case _ Gloss=the|MGloss=PIV
-4 mga mga DET _ Number=Plur|PronType=Ind 5 det _ Gloss=PLUR
-5 bata bata NOUN _ _ 1 nsubj _ Gloss=child
-6 ng ng ADP _ Case=Gen 8 case _ Gloss=DET
-7 mga mga DET _ Number=Plur|PronType=Ind 8 det _ Gloss=PLUR
-8 liham liham NOUN _ _ 1 obj _ Gloss=letter|SpaceAfter=No
-9 . . PUNCT _ _ 1 punct _ Gloss=.
-
-# sent_id = shopen-3.114b
-# text = Susulatin lahat ng mga bata ang mga liham.
-# source = Schachter and Otanes, 1972:147-8
-# gloss = FUT-write-OP all ACT PL child PIV PL letter
-# text_en = The/some children will write all the letters
-1 Susulatin sulat VERB _ Aspect=Prog|Mood=Ind|Voice=Pass 0 root _ Gloss=will-be-written|MSeg=su-sulat-in|MGloss=FUT-write-OP
-2 lahat lahat DET _ PronType=Tot 8 det _ Gloss=all
-3 ng ng ADP _ Case=Gen 5 case _ Gloss=DET
-4 mga mga DET _ Number=Plur|PronType=Ind 5 det _ Gloss=PLUR
-5 bata bata NOUN _ _ 1 obj:agent _ Gloss=child
-6 ang ang ADP _ Case=Nom 8 case _ Gloss=the|MGloss=PIV
-7 mga mga DET _ Number=Plur|PronType=Ind 8 det _ Gloss=PLUR
-8 liham liham NOUN _ _ 1 nsubj:pass _ Gloss=letter|SpaceAfter=No
-9 . . PUNCT _ _ 1 punct _ Gloss=.
-
-# sent_id = shopen-3.115a
-# text = Nagalala ang lolo sa kaniyang sarili.
-# source = Schachter, 1977:292
-# gloss = AP-worry PIV grandfather DIR his-LINK self
-# text_en = Grandfather worried about himself
-1 Nagalala alala VERB _ Aspect=Perf|Mood=Ind|Voice=Act 0 root _ Gloss=worried|MSeg=nag-alala|MGloss=AP-worry
-2 ang ang ADP _ Case=Nom 3 case _ Gloss=the|MGloss=PIV
-3 lolo lolo NOUN _ _ 1 nsubj _ Gloss=grandfather
-4 sa sa ADP _ Case=Dat 6 case _ Gloss=to
-5 kaniyang siya PRON _ Case=Dat|Link=Yes|Number=Sing|Person=3|PronType=Prs 6 nmod _ Gloss=him|MSeg=kaniya-ng|MGloss=his-LINK
-6 sarili sarili PRON _ PronType=Prs|Reflex=Yes 1 obl _ Gloss=self|SpaceAfter=No
-7 . . PUNCT _ _ 1 punct _ Gloss=.
-
-# sent_id = shopen-3.115b
-# text = Inalala ng lolo ang kaniyang sarili.
-# source = Schachter, 1977:292
-# gloss = PERF-worry-OP ACT grandfather PIV his-LINK self
-# text_en = Grandfather worried about himself
-1 Inalala alala VERB _ Aspect=Perf|Mood=Ind|Voice=Pass 0 root _ Gloss=worried|MSeg=in-alala-0|MGloss=PERF-worry-OP
-2 ng ng ADP _ Case=Gen 3 case _ Gloss=DET
-3 lolo lolo NOUN _ _ 1 obj:agent _ Gloss=grandfather
-4 ang ang ADP _ Case=Nom 6 case _ Gloss=the|MGloss=PIV
-5 kaniyang siya PRON _ Case=Dat|Link=Yes|Number=Sing|Person=3|PronType=Prs 6 nmod _ Gloss=him|MSeg=kaniya-ng|MGloss=his-LINK
-6 sarili sarili PRON _ PronType=Prs|Reflex=Yes 1 nsubj _ Gloss=self|SpaceAfter=No
-7 . . PUNCT _ _ 1 punct _ Gloss=.
-
-# sent_id = shopen-3.117a
-# text = Iniabot niya sa bata ang kaniyang sariling larawan.
-# gloss = PERF-OP-hand he(ACT) DIR child PIV his-LINK self-LINK picture
-# text_en = He[i] handed the child[j] a picture of himself[i,j]
-1 Iniabot abot VERB _ Aspect=Perf|Mood=Ind|Voice=Pass 0 root _ Gloss=handed|MSeg=in-i-abot|MGloss=PERF-OP-hand
-2 niya siya PRON _ Case=Gen|Number=Sing|Person=3|PronType=Prs 1 obj:agent _ Gloss=him|MGloss=he(ACT)
-3 sa sa ADP _ Case=Dat 4 case _ Gloss=to
-4 bata bata NOUN _ _ 1 obl _ Gloss=child
-5 ang ang ADP _ Case=Nom 8 case _ Gloss=the|MGloss=PIV
-6 kaniyang siya PRON _ Case=Dat|Link=Yes|Number=Sing|Person=3|PronType=Prs 7 nmod _ Gloss=him|MSeg=kaniya-ng|MGloss=his-LINK
-7 sariling sarili PRON _ Link=Yes|PronType=Prs|Reflex=Yes 8 nmod _ Gloss=self|MSeg=sarili-ng|MGloss=self-LINK
-8 larawan larawan NOUN _ _ 1 nsubj:pass _ Gloss=picture|SpaceAfter=No
-9 . . PUNCT _ _ 1 punct _ Gloss=.
-
-# sent_id = shopen-3.117b
-# text = Tumanggap ang Rosa ng sulat para sa bata sa kaniyang sarili.
-# gloss = [AP]-receive PIV Rosa OBJ letter BEN BEN child DIR her-LINK self
-# text_en = Rosa[i] received a letter for the child[j] from herself[i]/him-herself[j]
-1 Tumanggap tanggap VERB _ Aspect=Perf|Mood=Ind|Voice=Act 0 root _ Gloss=received|MSeg=t[um]anggap|MGloss=[AP]-receive
-2 ang ang ADP _ Case=Nom 3 case _ Gloss=the|MGloss=PIV
-3 Rosa Rosa PROPN _ Gender=Fem 1 nsubj _ Gloss=Rosa
-4 ng ng ADP _ Case=Gen 5 case _ Gloss=DET
-5 sulat sulat NOUN _ _ 1 obj _ Gloss=letter
-6 para para ADP _ _ 8 case _ Gloss=for|MGloss=BEN
-7 sa sa ADP _ Case=Dat 8 case _ Gloss=to
-8 bata bata NOUN _ _ 1 obl _ Gloss=child
-9 sa sa ADP _ Case=Dat 11 case _ Gloss=from
-10 kaniyang siya PRON _ Case=Dat|Link=Yes|Number=Sing|Person=3|PronType=Prs 11 nmod _ Gloss=him|MSeg=kaniya-ng|MGloss=his-LINK
-11 sarili sarili PRON _ PronType=Prs|Reflex=Yes 1 obl _ Gloss=self|SpaceAfter=No
-12 . . PUNCT _ _ 1 punct _ Gloss=.
-
-# sent_id = shopen-3.118a
-# text = Magbigay ka sa kaniya ng kape.
-# source = Schachter, 1977
-# gloss = AP-give you(PIV) DIR him OBJ coffee
-# text_en = Give him some coffee!
-1 Magbigay bigay VERB _ Mood=Imp|Voice=Act 0 root _ Gloss=give|MSeg=mag-bigay|MGloss=AP-give
-2 ka ikaw PRON _ Case=Nom|Number=Sing|Person=2|PronType=Prs 1 nsubj _ Gloss=you|MGloss=you(PIV)
-3 sa sa ADP _ Case=Dat 4 case _ Gloss=to|MGloss=DIR
-4 kaniya siya PRON _ Case=Dat|Number=Sing|Person=3|PronType=Prs 1 obl _ Gloss=him
-5 ng ng ADP _ Case=Gen 6 case _ Gloss=DET
-6 kape kape NOUN _ _ 1 obj _ Gloss=coffee|SpaceAfter=No
-7 . . PUNCT _ _ 1 punct _ Gloss=.
-
-# sent_id = shopen-3.118b
-# text = Bigyan mo siya ng kape.
-# source = Schachter, 1977
-# gloss = give-DP you(ACT) him(PIV) OBJ coffee
-# text_en = Give him some coffee!
-1 Bigyan bigay VERB _ Mood=Imp|Voice=Lfoc 0 root _ Gloss=give|MSeg=bigy-an|MGloss=give-DP
-2 mo ikaw PRON _ Case=Gen|Number=Sing|Person=2|PronType=Prs 1 obj:agent _ Gloss=you|MGloss=you(ACT)
-3 siya siya PRON _ Case=Nom|Number=Sing|Person=3|PronType=Prs 1 nsubj:lfoc _ Gloss=he|MGloss=him(PIV)
-4 ng ng ADP _ Case=Gen 5 case _ Gloss=DET
-5 kape kape NOUN _ _ 1 iobj:patient _ Gloss=coffee|SpaceAfter=No
-6 . . PUNCT _ _ 1 punct _ Gloss=.
-
-# sent_id = shopen-3.119a
-# text = Walisan natin ang sahig.
-# source = Schachter and Otanes, 1972:407-9
-# gloss = Sweep-OP us(DU.ACT) PIV floor
-# text_en = Let's sweep the floor
-1 Walisan walis VERB _ Mood=Imp|Voice=Pass 0 root _ Gloss=sweep|MSeg=walis-an|MGloss=sweep-OP
-2 natin ako PRON _ Case=Gen|Clusivity=In|Number=Plur|Person=1|PronType=Prs 1 obj:agent _ Gloss=us|MGloss=us(DU.ACT)
-3 ang ang ADP _ Case=Nom 4 case _ Gloss=the|MGloss=PIV
-4 sahig sahig NOUN _ _ 1 nsubj:pass _ Gloss=floor|SpaceAfter=No
-5 . . PUNCT _ _ 1 punct _ Gloss=.
-
-# sent_id = shopen-3.119b
-# text = Walisan nila ang sahig.
-# source = Schachter and Otanes, 1972:407-9
-# gloss = Sweep-OP they(ACT) PIV floor
-# text_en = I want them to sweep the floor
-1 Walisan walis VERB _ Mood=Imp|Voice=Pass 0 root _ Gloss=sweep|MSeg=walis-an|MGloss=sweep-OP
-2 nila sila PRON _ Case=Gen|Number=Plur|Person=3|PronType=Prs 1 obj:agent _ Gloss=them|MGloss=they(ACT)
-3 ang ang ADP _ Case=Nom 4 case _ Gloss=the|MGloss=PIV
-4 sahig sahig NOUN _ _ 1 nsubj:pass _ Gloss=floor|SpaceAfter=No
-5 . . PUNCT _ _ 1 punct _ Gloss=.
-
-# sent_id = shopen-3.120a
-# text = Nagatubili siyang humiram ng pera sa banko.
-# source = Schachter, 1972
-# gloss = AP-hesitate he(PIV)-LINK [AP]-borrow OBJ money DIR bank
-# text_en = He hesitated to borrow money from a/the bank
-1 Nagatubili atubili VERB _ Aspect=Perf|Mood=Ind|Voice=Act 0 root _ Gloss=hesitated|MSeg=nag-atubili|MGloss=AP-hesitate
-2 siyang siya PRON _ Case=Nom|Link=Yes|Number=Sing|Person=3|PronType=Prs 1 nsubj _ Gloss=he|MSeg=siya-ng|MGloss=he(PIV)-LINK
-3 humiram hiram VERB _ Aspect=Perf|Mood=Ind|Voice=Act 1 xcomp _ Gloss=borrow|MSeg=h[um]iram|MGloss=[AP]-borrow
-4 ng ng ADP _ Case=Gen 5 case _ Gloss=DET|MGloss=OBJ
-5 pera pera NOUN _ _ 3 obj _ Gloss=money
-6 sa sa ADP _ Case=Dat 7 case _ Gloss=to|MGloss=DIR
-7 banko banko NOUN _ _ 3 obl _ Gloss=bank|SpaceAfter=No
-8 . . PUNCT _ _ 1 punct _ Gloss=.
-
-# sent_id = shopen-3.120b
-# text = Nagatubili siyang hiramin ang pera sa banko.
-# source = Schachter, 1972
-# gloss = AP-hesitate he(PIV)-LINK borrow-OP PIV money DIR bank
-# text_en = He hesitated to borrow the money from the bank
-1 Nagatubili atubili VERB _ Aspect=Perf|Mood=Ind|Voice=Act 0 root _ Gloss=hesitated|MSeg=nag-atubili|MGloss=AP-hesitate
-2 siyang siya PRON _ Case=Nom|Link=Yes|Number=Sing|Person=3|PronType=Prs 1 nsubj _ Gloss=he|MSeg=siya-ng|MGloss=he(PIV)-LINK
-3 hiramin hiram VERB _ Aspect=Perf|Mood=Ind|Voice=Pass 1 xcomp _ Gloss=borrow|MSeg=hiram-in|MGloss=borrow-OP
-4 ang ang ADP _ Case=Nom 5 case _ Gloss=the|MGloss=PIV
-5 pera pera NOUN _ _ 3 nsubj:pass _ Gloss=money
-6 sa sa ADP _ Case=Dat 7 case _ Gloss=to|MGloss=DIR
-7 banko banko NOUN _ _ 3 obl _ Gloss=bank|SpaceAfter=No
-8 . . PUNCT _ _ 1 punct _ Gloss=.
-
-# sent_id = shopen-3.121a
-# text = Gusto ni Juan suriin siya ng doktor.
-# source = Schachter, 1977:295
-# gloss = want ACT John(LINK) examine-OP he(PIV) ACT doctor
-# text_en = John wants the doctor to examine him
-# The verb gusto seems to have only the patient focus voice. But here it appears in its base form, without aspectual inflection.
-# https://www.tagalog.com/words/gusto.php suggests that "gusto" does not inflect.
-# The patient focus means that the agent (which is the only argument) must appear in the genitive case.
-1 Gusto gusto VERB _ Aspect=Hab|Voice=Pass 0 root _ Gloss=want
-2 ni ni ADP _ Case=Gen 3 case _ Gloss=DET
-3 Juan Juan PROPN _ Gender=Masc|Link=Yes 1 obj:agent _ Gloss=Juan|MGloss=John(LINK)
-4 suriin suri VERB _ Aspect=Perf|Mood=Ind|Voice=Pass 1 ccomp _ Gloss=examine|MSeg=suri-in|MGloss=examine-OP
-5 siya siya PRON _ Case=Nom|Number=Sing|Person=3|PronType=Prs 4 nsubj:pass _ Gloss=he|MGloss=he(PIV)
-6 ng ng ADP _ Case=Gen 7 case _ Gloss=DET|MGloss=ACT
-7 doktor doktor NOUN _ _ 4 obj:agent _ Gloss=doctor|SpaceAfter=No
-8 . . PUNCT _ _ 1 punct _ Gloss=.
-
-# sent_id = shopen-3.122a
-# text = Masagwa ang tumatanda.
-# gloss = disagreeable PIV [AP]-IMPERF-become-old
-# text_en = It is disagreeable to become old
-1 Masagwa masagwa ADJ _ Degree=Pos 0 root _ Gloss=disagreeable
-2 ang ang ADP _ Case=Nom 3 case _ Gloss=the|MGloss=PIV
-3 tumatanda tatanda VERB _ Aspect=Imp|Mood=Ind|Voice=Act 1 csubj _ Gloss=to-become-old|MGloss=[AP]-IMPERF-become-old|MSeg=t[um]a-tanda|SpaceAfter=No
-4 . . PUNCT _ _ 1 punct _ Gloss=.
-
-# sent_id = shopen-3.122b
-# text = Gusto niyang gumanda.
-# gloss = want he/she(ACT)-LINK [AP]-beautiful
-# text_en = She wants to become beautiful
-1 Gusto gusto VERB _ Aspect=Hab|Voice=Pass 0 root _ Gloss=want
-2 niyang siya PRON _ Case=Gen|Link=Yes|Number=Sing|Person=3|PronType=Prs 1 obj:agent _ Gloss=him|MSeg=niya-ng|MGloss=he/she(ACT)-LINK
-3 gumanda ganda VERB _ Aspect=Perf|Mood=Ind|Voice=Act 1 xcomp _ Gloss=become-beautiful|MGloss=[AP]-beautiful|MSeg=g[um]anda|SpaceAfter=No
-4 . . PUNCT _ _ 1 punct _ Gloss=.
-
-# sent_id = shopen-3.122c
-# text = Gusto kong tumanggap ng gantimpala.
-# gloss = want I(ACT)-LINK [AP]-receive OBJ prize
-# text_en = I want to be the recipient of the prize
-1 Gusto gusto VERB _ Aspect=Hab|Voice=Pass 0 root _ Gloss=want
-2 kong ako PRON _ Case=Gen|Link=Yes|Number=Sing|Person=1|PronType=Prs 1 obj:agent _ Gloss=me|MSeg=ko-ng|MGloss=I(ACT)-LINK
-3 tumanggap tanggap VERB _ Aspect=Perf|Mood=Ind|Voice=Act 1 xcomp _ Gloss=received|MSeg=t[um]anggap|MGloss=[AP]-receive
-4 ng ng ADP _ Case=Gen 5 case _ Gloss=DET|MGloss=OBJ
-5 gantimpala gantimpala NOUN _ _ 3 obj _ Gloss=prize|SpaceAfter=No
-6 . . PUNCT _ _ 1 punct _ Gloss=.
-
-# sent_id = shopen-3.122d
-# text = Gusto kong matanggap ang gantimpala.
-# gloss = want I(ACT)-LINK OP-receive PIV prize
-# text_en = I want to receive the prize
-1 Gusto gusto VERB _ Aspect=Hab|Voice=Pass 0 root _ Gloss=want
-2 kong ako PRON _ Case=Gen|Link=Yes|Number=Sing|Person=1|PronType=Prs 1 obj:agent _ Gloss=me|MSeg=ko-ng|MGloss=I(ACT)-LINK
-3 matanggap tanggap VERB _ Aspect=Perf|Mood=Ind|Voice=Pass 1 xcomp _ Gloss=received|MSeg=ma-tanggap|MGloss=OP-receive
-4 ang ang ADP _ Case=Nom 5 case _ Gloss=the|MGloss=PIV
-5 gantimpala gantimpala NOUN _ _ 3 nsubj:pass _ Gloss=prize|SpaceAfter=No
-6 . . PUNCT _ _ 1 punct _ Gloss=.
-
-# sent_id = shopen-3.123
-# text = Ayaw kong mamatay sa Maynila.
-# gloss = not.want I(ACT)-LINK AP-die DIR Manila
-# text_en = I don't want to die in Manila
-1 Ayaw ayaw VERB _ Aspect=Hab|Voice=Pass 0 root _ Gloss=not-want|MGloss=not.want
-2 kong ako PRON _ Case=Gen|Link=Yes|Number=Sing|Person=1|PronType=Prs 1 obj:agent _ Gloss=me|MSeg=ko-ng|MGloss=I(ACT)-LINK
-3 mamatay patay VERB _ Aspect=Perf|Mood=Ind|Voice=Act 1 xcomp _ Gloss=die|MSeg=ma-matay|MGloss=AP-die
-4 sa sa ADP _ Case=Dat 5 case _ Gloss=to|MGloss=DIR
-5 Maynila Maynila PROPN _ _ 3 obl _ Gloss=Manila|SpaceAfter=No
-6 . . PUNCT _ _ 1 punct _ Gloss=.
-
-# sent_id = shopen-3.124a
-# text = Binisita ni Juan ang hari nang nagiisa.
-# gloss = [PERF]-visit(OP) ACT Juan PIV king ADV AP.IMPERF-one
-# text_en = Juan visited the king alone [either Juan or the king is alone]
-1 Binisita bisita VERB _ Aspect=Perf|Mood=Ind|Voice=Pass 0 root _ Gloss=visited|MSeg=b[in]isita|MGloss=[PERF]-visit(OP)
-2 ni ni ADP _ Case=Gen 3 case _ Gloss=DET|MGloss=ACT
-3 Juan Juan PROPN _ Gender=Masc 1 obj:agent _ Gloss=Juan|MGloss=John(LINK)
-4 ang ang ADP _ Case=Nom 5 case _ Gloss=the|MGloss=PIV
-5 hari hari NOUN _ _ 1 nsubj:pass _ Gloss=king
-6 nang nang SCONJ _ _ 7 mark _ Gloss=while|MGloss=ADV
-7 nagiisa iisa VERB _ Aspect=Imp|Mood=Ind|Voice=Act 1 advcl _ Gloss=being-alone|MGloss=AP.IMPERF-one|MSeg=nag-iisa|SpaceAfter=No
-8 . . PUNCT _ _ 1 punct _ Gloss=.
-
-# sent_id = shopen-3.124b
-# text = Bumisita si Juan sa hari nang nagiisa.
-# gloss = [AP.PERF]-visit PIV Juan DAT king ADV AP.IMPERF-one
-# text_en = Juan visited the king alone [only Juan is alone]
-1 Bumisita bisita VERB _ Aspect=Perf|Mood=Ind|Voice=Act 0 root _ Gloss=visited|MSeg=b[um]isita|MGloss=[AP.PERF]-visit
-2 si si ADP _ Case=Nom 3 case _ Gloss=the|MGloss=PIV
-3 Juan Juan PROPN _ Gender=Masc 1 nsubj _ Gloss=Juan|MGloss=John(LINK)
-4 sa sa ADP _ Case=Dat 5 case _ Gloss=to|MGloss=DAT
-5 hari hari NOUN _ _ 1 obl _ Gloss=king
-6 nang nang SCONJ _ _ 7 mark _ Gloss=while|MGloss=ADV
-7 nagiisa iisa VERB _ Aspect=Imp|Mood=Ind|Voice=Act 1 advcl _ Gloss=being-alone|MGloss=AP.IMPERF-one|MSeg=nag-iisa|SpaceAfter=No
-8 . . PUNCT _ _ 1 punct _ Gloss=.
-
-# sent_id = shopen-3.124c
-# text = Hinuli ng polis ang mgananakaw nang pumapasok sa banko.
-# gloss = PERF-catch(OP) ACT police PIV thief ADV AP.IMPERF:enter DAT bank
-# text_en = The police caught the thief entering the bank [either thief or police are entering]
-1 Hinuli huli VERB _ Aspect=Perf|Mood=Ind|Voice=Pass 0 root _ Gloss=caught|MSeg=h[in]uli|MGloss=PERF-catch(OP)
-2 ng ng ADP _ Case=Gen 3 case _ Gloss=DET|MGloss=ACT
-3 polis polis NOUN _ _ 1 obj:agent _ Gloss=police
-4 ang ang ADP _ Case=Nom 5 case _ Gloss=the|MGloss=PIV
-5 mgananakaw mgananakaw NOUN _ _ 1 nsubj:pass _ Gloss=thief
-6 nang nang SCONJ _ _ 7 mark _ Gloss=while|MGloss=ADV
-7 pumapasok pasok VERB _ Aspect=Imp|Mood=Ind|Voice=Act 1 advcl _ Gloss=entering|MSeg=p[um]a-pasok|MGloss=[AP]-IMPERF-enter
-8 sa sa ADP _ Case=Dat 9 case _ Gloss=to|MGloss=DAT
-9 banko banko NOUN _ _ 7 obl _ Gloss=bank|SpaceAfter=No
-10 . . PUNCT _ _ 1 punct _ Gloss=.
-
-# sent_id = shopen-3.124d
-# text = Nanghuli ng mgananakaw ang polis nang pumapasok sa banko.
-# gloss = AP.PERF-catch OBJ thief PIV police ADV AV.IMPERF:enter DAT bank
-# text_en = The police caught the thief entering the bank [either thief or police are entering]
-1 Nanghuli huli VERB _ Aspect=Perf|Mood=Ind|Voice=Act 0 root _ Gloss=caught|MSeg=nang-huli|MGloss=AP.PERF-catch
-2 ng ng ADP _ Case=Gen 3 case _ Gloss=DET|MGloss=OBJ
-3 mgananakaw mgananakaw NOUN _ _ 1 obj _ Gloss=thief
-4 ang ang ADP _ Case=Nom 5 case _ Gloss=the|MGloss=PIV
-5 polis polis NOUN _ _ 1 nsubj _ Gloss=police
-6 nang nang SCONJ _ _ 7 mark _ Gloss=while|MGloss=ADV
-7 pumapasok pasok VERB _ Aspect=Imp|Mood=Ind|Voice=Act 1 advcl _ Gloss=entering|MSeg=p[um]a-pasok|MGloss=[AP]-IMPERF-enter
-8 sa sa ADP _ Case=Dat 9 case _ Gloss=to|MGloss=DAT
-9 banko banko NOUN _ _ 7 obl _ Gloss=bank|SpaceAfter=No
-10 . . PUNCT _ _ 1 punct _ Gloss=.
-