From 41374773fcce3d62d5300766cd9d8854f33d5d82 Mon Sep 17 00:00:00 2001 From: pszenny <pszenny@e-science.pl> Date: Fri, 29 Apr 2022 12:51:32 +0200 Subject: [PATCH] instruction adjustment after switching to UD_29 and download fix from new source Update README.md small fix in performance.md small fix in performance.md - got rid of models that were trained on data with sentences of form "____" --- README.md | 2 +- combo/utils/download.py | 11 ++- docs/models.md | 16 ++--- docs/performance.md | 155 ++++++++++++++++++++++++++-------------- docs/prediction.md | 2 +- 5 files changed, 122 insertions(+), 64 deletions(-) diff --git a/README.md b/README.md index 0b0cfc7..ccf3a41 100644 --- a/README.md +++ b/README.md @@ -24,7 +24,7 @@ Run the following commands in your Python console to make predictions with a pre ```python from combo.predict import COMBO -nlp = COMBO.from_pretrained("polish-herbert-base") +nlp = COMBO.from_pretrained("polish-herbert-base-ud29") sentence = nlp("COVID-19 to ostra choroba zakaźna układu oddechowego wywołana zakażeniem wirusem SARS-CoV-2.") ``` Predictions are accessible as a list of token attributes: diff --git a/combo/utils/download.py b/combo/utils/download.py index 003b64c..1729270 100644 --- a/combo/utils/download.py +++ b/combo/utils/download.py @@ -9,14 +9,21 @@ from requests import adapters, exceptions logger = logging.getLogger(__name__) -_URL = "http://mozart.ipipan.waw.pl/~mklimaszewski/models/{name}.tar.gz" +DATA_TO_PATH = { + "enhanced" : "iwpt_2020", + "iwpt2021" : "iwpt_2021", + "ud25" : "ud_25", + "ud27" : "ud_27", + "ud29" : "ud_29"} +_URL = "http://s3.clarin-pl.eu/models/combo/{data}/{model}.tar.gz" _HOME_DIR = os.getenv("HOME", os.curdir) _CACHE_DIR = os.getenv("COMBO_DIR", os.path.join(_HOME_DIR, ".combo")) def download_file(model_name, force=False): _make_cache_dir() - url = _URL.format(name=model_name) + data = model_name.split("-")[-1] + url = _URL.format(name=model_name, data=DATA_TO_PATH[data]) local_filename = url.split("/")[-1] location = os.path.join(_CACHE_DIR, local_filename) if os.path.exists(location) and not force: diff --git a/docs/models.md b/docs/models.md index f2d7696..31fa78a 100644 --- a/docs/models.md +++ b/docs/models.md @@ -2,35 +2,35 @@ COMBO provides pre-trained models for: - morphosyntactic prediction (i.e. part-of-speech tagging, morphosyntactic analysis, lemmatisation and dependency parsing) trained on the treebanks from [Universal Dependencies repository](https://universaldependencies.org) ([Zeman et al. 2020](https://lindat.mff.cuni.cz/repository/xmlui/handle/11234/1-3424)), -- enhanced dependency parsing trained on IWPT 2020 shared task [data](https://universaldependencies.org/iwpt20/data.html) ([Bouma et al. 2020](https://www.aclweb.org/anthology/2020.iwpt-1.16.pdf)). +- enhanced dependency parsing trained on IWPT 2020 shared task [data](https://universaldependencies.org/iwpt20/data.html) ([Bouma et al. 2020](https://www.aclweb.org/anthology/2020.iwpt-1.16.pdf)) and IWPT 2021 shared task [data](https://universaldependencies.org/iwpt21/data.html). ## Pre-trained models -**Morphosyntactic prediction models** trained on the selected UD treebanks version 2.7 and their **evaluation results** are listed in [Model performance (UD2.7)](https://gitlab.clarin-pl.eu/syntactic-tools/combo/-/blob/master/docs/performance.md) table. +**Morphosyntactic prediction models** trained on the selected UD treebanks version 2.9 and their **evaluation results** are listed in [Model performance (UD2.9)](https://gitlab.clarin-pl.eu/syntactic-tools/combo/-/blob/master/docs/performance.md) table. -**Morphosyntactic prediction models** trained on the seleted UD treebanks version 2.5 and **enhanced parsing models** are listed in the spreadsheets: [UD2.5-trained COMBO models](https://docs.google.com/spreadsheets/d/1WFYc2aLRa1jw7le030HOacv9fc4zmtqiZtRQY6gl5mc/edit#gid=0) and [enhanced COMBO models](https://docs.google.com/spreadsheets/d/1WFYc2aLRa1jw7le030HOacv9fc4zmtqiZtRQY6gl5mc/edit#gid=1757180324). +**Morphosyntactic prediction models** trained on the seleted UD treebanks version 2.5, version 2.7 and **enhanced parsing models** are listed in the spreadsheets: [UD2.7-trained COMBO models](https://docs.google.com/spreadsheets/d/1WFYc2aLRa1jw7le030HOacv9fc4zmtqiZtRQY6gl5mc/edit#gid=1459988845), [UD2.5-trained COMBO models](https://docs.google.com/spreadsheets/d/1WFYc2aLRa1jw7le030HOacv9fc4zmtqiZtRQY6gl5mc/edit#gid=0) and [enhanced COMBO models](https://docs.google.com/spreadsheets/d/1WFYc2aLRa1jw7le030HOacv9fc4zmtqiZtRQY6gl5mc/edit#gid=1757180324). ### License Models are distributed under the same license as datasets used for their training. -See [Universal Dependencies v2.7 License Agreement](https://lindat.mff.cuni.cz/repository/xmlui/page/license-ud-2.7) and [Universal Dependencies v2.5 License Agreement](https://lindat.mff.cuni.cz/repository/xmlui/page/licence-UD-2.5) for details. +See [Universal Dependencies v2.9 License Agreement](https://lindat.mff.cuni.cz/repository/xmlui/page/license-ud-2.9), [Universal Dependencies v2.7 License Agreement](https://lindat.mff.cuni.cz/repository/xmlui/page/license-ud-2.7) and [Universal Dependencies v2.5 License Agreement](https://lindat.mff.cuni.cz/repository/xmlui/page/licence-UD-2.5) for details. ## Automatic download -The pre-trained models can be automatically downloaded with the `from_pretrained` method in the Python mode. Select the model name of a pre-trained model (see the column **Model name** in [Model performance (UD2.7)](https://gitlab.clarin-pl.eu/syntactic-tools/combo/-/blob/master/docs/performance.md), [UD2.5-trained COMBO models](https://docs.google.com/spreadsheets/d/1WFYc2aLRa1jw7le030HOacv9fc4zmtqiZtRQY6gl5mc/edit#gid=0) and [enhanced COMBO models](https://docs.google.com/spreadsheets/d/1WFYc2aLRa1jw7le030HOacv9fc4zmtqiZtRQY6gl5mc/edit#gid=1757180324)) and pass the name as an attribute of the `from_pretrained` method: +The pre-trained models can be automatically downloaded with the `from_pretrained` method in the Python mode. Select the model name of a pre-trained model (see the column **Model name** in [Model performance (UD2.9)](https://gitlab.clarin-pl.eu/syntactic-tools/combo/-/blob/master/docs/performance.md), [UD2.7-trained COMBO models](https://docs.google.com/spreadsheets/d/1WFYc2aLRa1jw7le030HOacv9fc4zmtqiZtRQY6gl5mc/edit#gid=1459988845), [UD2.5-trained COMBO models](https://docs.google.com/spreadsheets/d/1WFYc2aLRa1jw7le030HOacv9fc4zmtqiZtRQY6gl5mc/edit#gid=0) and [enhanced COMBO models](https://docs.google.com/spreadsheets/d/1WFYc2aLRa1jw7le030HOacv9fc4zmtqiZtRQY6gl5mc/edit#gid=1757180324)) and pass the name as an attribute of the `from_pretrained` method: ```python from combo.predict import COMBO -nlp = COMBO.from_pretrained("polish-herbert-base") +nlp = COMBO.from_pretrained("polish-herbert-base-ud29") ``` If the model name doesn't match any model on the pre-trained model lists, COMBO looks for a model in local env. ## Manual download -If you want to use COMBO in the command-line mode, you need to manually download a pre-trained model. The pre-trained models can be manually downloaded to a local disk with the `wget` package. The links to the pre-trained models are listed in the column **Model name** in [Model performance (UD2.7)](https://gitlab.clarin-pl.eu/syntactic-tools/combo/-/blob/master/docs/performance.md), or **Model link** in [UD2.5-trained COMBO models](https://docs.google.com/spreadsheets/d/1WFYc2aLRa1jw7le030HOacv9fc4zmtqiZtRQY6gl5mc/edit#gid=0) and [enhanced COMBO models](https://docs.google.com/spreadsheets/d/1WFYc2aLRa1jw7le030HOacv9fc4zmtqiZtRQY6gl5mc/edit#gid=1757180324). +If you want to use COMBO in the command-line mode, you need to manually download a pre-trained model. The pre-trained models can be manually downloaded to a local disk with the `wget` package. The links to the pre-trained models are listed in the column **Model name** in [Model performance (UD2.9)](https://gitlab.clarin-pl.eu/syntactic-tools/combo/-/blob/master/docs/performance.md), or **Model link** in [UD2.7-trained COMBO models](https://docs.google.com/spreadsheets/d/1WFYc2aLRa1jw7le030HOacv9fc4zmtqiZtRQY6gl5mc/edit#gid=1459988845),[UD2.5-trained COMBO models](https://docs.google.com/spreadsheets/d/1WFYc2aLRa1jw7le030HOacv9fc4zmtqiZtRQY6gl5mc/edit#gid=0) and [enhanced COMBO models](https://docs.google.com/spreadsheets/d/1WFYc2aLRa1jw7le030HOacv9fc4zmtqiZtRQY6gl5mc/edit#gid=1757180324). ```bash -wget http://mozart.ipipan.waw.pl/~mklimaszewski/models/polish-herbert-base.tar.gz +wget http://s3.clarin-pl.eu/models/combo/ud_29/polish-herbert-base-ud29.tar.gz ``` The path to the downloaded model should be passed as a parameter for COMBO in CLI (see [prediction doc](prediction.md)). diff --git a/docs/performance.md b/docs/performance.md index ae97049..eb76ed9 100644 --- a/docs/performance.md +++ b/docs/performance.md @@ -1,58 +1,109 @@ # Model performance The models were trained with COMBO boosted with either FastText embeddings or BERT models (english-bert-base, polish-herbert-base, and polish-herbert-large). -We list here only models trained on the Universal Dependencies version 2.7 dataset, check [COMBO models spreadsheet](https://docs.google.com/spreadsheets/d/1WFYc2aLRa1jw7le030HOacv9fc4zmtqiZtRQY6gl5mc/edit?usp=sharing) +We list here only models trained on the Universal Dependencies version 2.9 dataset, check [COMBO models spreadsheet](https://docs.google.com/spreadsheets/d/1WFYc2aLRa1jw7le030HOacv9fc4zmtqiZtRQY6gl5mc/edit?usp=sharing) for more. -|Treebank |Model name |UPOS |XPOS |UFeats|AllTags|Lemmas|UAS |LAS |CLAS |MLAS |BLEX |Language model |LICENSE | -|-------------------------|--------------------|-----|------|------|-------|------|-----|-----|-----|-----|-----|---------------|----------------------------------------------------------------------------------------| -|UD_English-EWT |[english-bert-base](http://mozart.ipipan.waw.pl/~mklimaszewski/models/english-bert-base.tar.gz) |96.53|96.41 |97.34 |95.04 |97.72 |92.17|89.75|87.25|82.14|84.65|bert-base-cased|https://github.com/UniversalDependencies/UD_English-EWT/blob/r2.7/LICENSE.txt | -|UD_Polish_PDB |[polish-herbert-base](http://mozart.ipipan.waw.pl/~mklimaszewski/models/polish-herbert-base.tar.gz) |98.93|96.42 |96.79 |95.73 |98.08 |95.53|93.81|92.30|87.44|89.86|herbert-base |https://github.com/UniversalDependencies/UD_Polish-PDB/blob/r2.7/LICENSE.txt | -|UD_Polish_PDB |[polish-herbert-large](http://mozart.ipipan.waw.pl/~mklimaszewski/models/polish-herbert-large.tar.gz)|99.04|96.65 |96.97 |95.95 |98.13 |95.48|93.84|92.31|87.84|90.04|herbert-large |https://github.com/UniversalDependencies/UD_Polish-PDB/blob/r2.7/LICENSE.txt | -|UD_Afrikaans-AfriBooms |[afrikaans-ud27](http://mozart.ipipan.waw.pl/~mklimaszewski/models/afrikaans-ud27.tar.gz) |97.13|91.79 |96.54 |91.32 |96.78 |87.43|84.30|78.08|72.56|74.06|fastText |https://github.com/UniversalDependencies/UD_Afrikaans-AfriBooms/blob/r2.7/LICENSE.txt | -|UD_Armenian-ArmTDP |[armenian-ud27](http://mozart.ipipan.waw.pl/~mklimaszewski/models/armenian-ud27.tar.gz) |94.23|100.00|88.04 |85.99 |93.88 |82.77|76.04|70.08|58.26|65.62|fastText |https://github.com/UniversalDependencies/UD_Armenian-ArmTDP/blob/r2.7/LICENSE.txt | -|UD_Basque-BDT |[basque-ud27](http://mozart.ipipan.waw.pl/~mklimaszewski/models/basque-ud27.tar.gz) |94.28|100.00|90.44 |87.52 |95.47 |84.64|80.44|78.82|67.33|74.95|fastText |https://github.com/UniversalDependencies/UD_Basque-BDT/blob/r2.7/LICENSE.txt | -|UD_Belarusian-HSE |[belarusian-ud27](http://mozart.ipipan.waw.pl/~mklimaszewski/models/belarusian-ud27.tar.gz) |98.13|96.33 |91.06 |89.24 |92.88 |83.91|79.84|75.87|67.39|68.81|fastText |https://github.com/UniversalDependencies/UD_Belarusian-HSE/blob/r2.7/LICENSE.txt | -|UD_Bulgarian-BTB |[bulgarian-ud27](http://mozart.ipipan.waw.pl/~mklimaszewski/models/bulgarian-ud27.tar.gz) |98.84|95.24 |97.33 |94.73 |97.44 |93.36|90.05|86.55|82.58|83.22|fastText |https://github.com/UniversalDependencies/UD_Bulgarian-BTB/blob/r2.7/LICENSE.txt | -|UD_Catalan-AnCora |[catalan-ud27](http://mozart.ipipan.waw.pl/~mklimaszewski/models/catalan-ud27.tar.gz) |98.68|98.60 |98.23 |97.63 |99.13 |92.92|90.62|86.35|83.81|85.67|fastText |https://github.com/UniversalDependencies/UD_Catalan-AnCora/blob/r2.7/LICENSE.txt | -|UD_Chinese-GSD |[chinese-ud27](http://mozart.ipipan.waw.pl/~mklimaszewski/models/chinese-ud27.tar.gz) |94.77|94.55 |99.18 |93.56 |98.93 |82.80|78.75|77.24|71.42|76.03|fastText |https://github.com/UniversalDependencies/UD_Chinese-GSD/blob/r2.7/LICENSE.txt | -|UD_Chinese-GSDSimp |[chinese-simp-ud27](http://mozart.ipipan.waw.pl/~mklimaszewski/models/chinese-simp-ud27.tar.gz) |94.86|94.70 |99.16 |93.70 |98.98 |83.47|79.50|77.93|72.54|76.70|fastText |https://github.com/UniversalDependencies/UD_Chinese-GSDSimp/blob/r2.7/LICENSE.txt | -|UD_Croatian-SET |[croatian-ud27](http://mozart.ipipan.waw.pl/~mklimaszewski/models/croatian-ud27.tar.gz) |97.48|94.09 |94.67 |93.06 |96.85 |89.45|85.46|82.34|75.32|78.86|fastText |https://github.com/UniversalDependencies/UD_Croatian-SET/blob/r2.7/LICENSE.txt | -|UD_Czech-PDT |[czech-ud27](http://mozart.ipipan.waw.pl/~mklimaszewski/models/czech-ud27.tar.gz) |99.01|96.60 |96.77 |95.78 |98.64 |93.51|91.67|90.18|86.24|88.74|fastText |https://github.com/UniversalDependencies/UD_Czech-PDT/blob/r2.7/LICENSE.txt | -|UD_Danish-DDT |[danish-ud27](http://mozart.ipipan.waw.pl/~mklimaszewski/models/danish-ud27.tar.gz) |97.08|100.00|96.20 |95.15 |96.89 |85.41|82.37|78.83|72.63|75.76|fastText |https://github.com/UniversalDependencies/UD_Danish-DDT/blob/r2.7/LICENSE.txt | -|UD_Dutch-Alpino |[dutch-ud27](http://mozart.ipipan.waw.pl/~mklimaszewski/models/dutch-ud27.tar.gz) |96.22|94.13 |95.97 |93.28 |95.78 |91.48|87.91|82.48|75.92|77.34|fastText |https://github.com/UniversalDependencies/UD_Dutch-Alpino/blob/r2.7/LICENSE.txt | -|UD_English-EWT |[english-ud27](http://mozart.ipipan.waw.pl/~mklimaszewski/models/english-ud27.tar.gz) |95.76|95.39 |96.59 |93.89 |97.63 |88.85|86.00|82.63|77.00|80.20|fastText |https://github.com/UniversalDependencies/UD_English-EWT/blob/r2.7/LICENSE.txt | -|UD_Estonian-EWT |[estonian-ud27](http://mozart.ipipan.waw.pl/~mklimaszewski/models/estonian-ud27.tar.gz) |90.61|93.62 |87.91 |83.79 |81.63 |74.98|68.33|63.71|53.27|49.69|fastText |https://github.com/UniversalDependencies/UD_Estonian-EWT/blob/r2.7/LICENSE.txt | -|UD_Finnish-TDT |[finnish-ud27](http://mozart.ipipan.waw.pl/~mklimaszewski/models/finnish-ud27.tar.gz) |95.89|97.98 |93.60 |92.24 |88.53 |89.43|86.46|84.32|77.06|72.07|fastText |https://github.com/UniversalDependencies/UD_Finnish-TDT/blob/r2.7/LICENSE.txt | -|UD_French-GSD |[french-ud27](http://mozart.ipipan.waw.pl/~mklimaszewski/models/french-ud27.tar.gz) |97.88|100.00|97.97 |97.07 |98.35 |92.70|90.67|86.19|82.54|84.06|fastText |https://github.com/UniversalDependencies/UD_French-GSD/blob/r2.7/LICENSE.txt | -|UD_Galician-CTG |[galician-ud27](http://mozart.ipipan.waw.pl/~mklimaszewski/models/galician-ud27.tar.gz) |97.22|95.62 |99.81 |95.17 |98.31 |85.44|82.41|76.72|69.65|75.10|fastText |https://github.com/UniversalDependencies/UD_Galician-CTG/blob/r2.7/LICENSE.txt | -|UD_German-GSD |[german-gsd-ud27](http://mozart.ipipan.waw.pl/~mklimaszewski/models/german-gsd-ud27.tar.gz) |94.26|96.62 |90.16 |84.68 |96.46 |86.78|82.01|76.78|59.23|72.22|fastText |https://github.com/UniversalDependencies/UD_German-GSD/blob/r2.7/LICENSE.txt | -|UD_German-HDT |[german-ud27](http://mozart.ipipan.waw.pl/~mklimaszewski/models/german-ud27.tar.gz) |98.39|98.35 |93.52 |93.07 |93.33 |96.90|95.86|93.60|83.53|83.60|fastText |https://github.com/UniversalDependencies/UD_German-HDT/blob/r2.7/LICENSE.txt | -|UD_Greek-GDT |[greek-ud27](http://mozart.ipipan.waw.pl/~mklimaszewski/models/greek-ud27.tar.gz) |97.34|97.37 |94.31 |93.45 |95.73 |91.19|88.78|84.30|76.26|78.58|fastText |https://github.com/UniversalDependencies/UD_Greek-GDT/blob/r2.7/LICENSE.txt | -|UD_Hebrew-HTB |[hebrew-ud27](http://mozart.ipipan.waw.pl/~mklimaszewski/models/hebrew-ud27.tar.gz) |96.94|96.91 |95.69 |94.72 |96.18 |89.21|86.07|80.27|73.70|75.56|fastText |https://github.com/UniversalDependencies/UD_Hebrew-HTB/blob/r2.7/LICENSE.txt | -|UD_Hindi-HDTB |[hindi-ud27](http://mozart.ipipan.waw.pl/~mklimaszewski/models/hindi-ud27.tar.gz) |97.38|96.93 |93.99 |91.81 |98.46 |94.59|91.39|87.59|77.73|86.12|fastText |https://github.com/UniversalDependencies/UD_Hindi-HDTB/blob/r2.7/LICENSE.txt | -|UD_Hungarian-Szeged |[hungarian-ud27](http://mozart.ipipan.waw.pl/~mklimaszewski/models/hungarian-ud27.tar.gz) |92.96|100.00|88.90 |86.37 |92.30 |80.91|75.29|73.44|59.11|66.32|fastText |https://github.com/UniversalDependencies/UD_Hungarian-Szeged/blob/r2.7/LICENSE.txt | -|UD_Icelandic-IcePaHC |[icelandic-ud27](http://mozart.ipipan.waw.pl/~mklimaszewski/models/icelandic-ud27.tar.gz) |96.50|92.07 |90.44 |85.24 |95.54 |87.16|83.02|77.58|64.71|73.51|fastText |https://github.com/UniversalDependencies/UD_Icelandic-IcePaHC/blob/r2.7/LICENSE.txt | -|UD_Indonesian-GSD |[indonesian-ud27](http://mozart.ipipan.waw.pl/~mklimaszewski/models/indonesian-ud27.tar.gz) |93.46|91.83 |95.51 |86.40 |98.93 |84.79|77.97|75.74|66.72|74.60|fastText |https://github.com/UniversalDependencies/UD_Indonesian-GSD/blob/r2.7/LICENSE.txt | -|UD_Irish-IDT |[irish-ud27](http://mozart.ipipan.waw.pl/~mklimaszewski/models/irish-ud27.tar.gz) |93.81|93.46 |73.25 |69.84 |90.77 |84.01|76.89|70.53|40.29|61.57|fastText |https://github.com/UniversalDependencies/UD_Irish-IDT/blob/r2.7/LICENSE.txt | -|UD_Italian-ISDT |[italian-ud27](http://mozart.ipipan.waw.pl/~mklimaszewski/models/italian-ud27.tar.gz) |98.11|97.96 |97.78 |97.02 |98.29 |93.13|91.02|86.76|83.25|84.65|fastText |https://github.com/UniversalDependencies/UD_Italian-ISDT/blob/r2.7/LICENSE.txt | -|UD_Maltese-MUDT |[maltese-ud27](http://mozart.ipipan.waw.pl/~mklimaszewski/models/maltese-ud27.tar.gz) |92.74|90.77 |100.00|90.01 |100.00|81.01|74.37|65.18|58.71|65.18|fastText |https://github.com/UniversalDependencies/UD_Maltese-MUDT/blob/r2.7/LICENSE.txt | -|UD_Norwegian-Bokmaal |[norwegian-ud27](http://mozart.ipipan.waw.pl/~mklimaszewski/models/norwegian-ud27.tar.gz) |97.50|100.00|95.98 |95.19 |98.04 |91.95|89.80|87.04|81.27|84.71|fastText |https://github.com/UniversalDependencies/UD_Norwegian-Bokmaal/blob/r2.7/LICENSE.txt | -|UD_Persian-PerDT |[persian-ud27](http://mozart.ipipan.waw.pl/~mklimaszewski/models/persian-ud27.tar.gz) |97.20|97.21 |97.72 |95.14 |98.84 |93.41|90.95|88.91|84.97|87.57|fastText |https://github.com/UniversalDependencies/UD_Persian-PerDT/blob/r2.7/LICENSE.txt | -|UD_Polish-PDB |[polish-ud27](http://mozart.ipipan.waw.pl/~mklimaszewski/models/polish-ud27.tar.gz) |98.20|94.26 |94.50 |93.23 |97.48 |92.83|90.44|88.07|81.29|85.54|fastText |https://github.com/UniversalDependencies/UD_Polish-PDB/blob/r2.7/LICENSE.txt | -|UD_Portuguese-GSD |[portuguese-ud27](http://mozart.ipipan.waw.pl/~mklimaszewski/models/portuguese-ud27.tar.gz) |98.06|98.08 |99.86 |97.97 |99.28 |92.72|91.15|86.93|84.76|86.15|fastText |https://github.com/UniversalDependencies/UD_Portuguese-GSD/blob/r2.7/LICENSE.txt | -|UD_Romanian-RRT |[romanian-ud27](http://mozart.ipipan.waw.pl/~mklimaszewski/models/romanian-ud27.tar.gz) |97.66|96.83 |96.92 |96.33 |98.32 |90.55|85.90|81.50|77.14|80.02|fastText |https://github.com/UniversalDependencies/UD_Romanian-RRT/blob/r2.7/LICENSE.txt | -|UD_Russian-Taiga |[russian-ud27](http://mozart.ipipan.waw.pl/~mklimaszewski/models/russian-ud27.tar.gz) |92.98|97.41 |88.42 |83.46 |92.42 |78.28|72.72|69.31|56.22|62.93|fastText |https://github.com/UniversalDependencies/UD_Russian-Taiga/blob/r2.7/LICENSE.txt | -|UD_Scottish_Gaelic-ARCOSG|[scottish_gaelic-ud27](http://mozart.ipipan.waw.pl/~mklimaszewski/models/scottish_gaelic-ud27.tar.gz)|94.11|87.39 |89.66 |85.41 |94.10 |84.35|78.60|72.35|62.43|67.05|fastText |https://github.com/UniversalDependencies/UD_Scottish_Gaelic-ARCOSG/blob/r2.7/LICENSE.txt| -|UD_Serbian-SET |[serbian-ud27](http://mozart.ipipan.waw.pl/~mklimaszewski/models/serbian-ud27.tar.gz) |97.94|93.51 |93.72 |92.63 |96.71 |90.61|87.38|84.70|77.06|81.33|fastText |https://github.com/UniversalDependencies/UD_Serbian-SET/blob/r2.7/LICENSE.txt | -|UD_Slovak-SNK |[slovak-ud27](http://mozart.ipipan.waw.pl/~mklimaszewski/models/slovak-ud27.tar.gz) |94.94|85.37 |90.24 |84.00 |95.30 |89.98|86.90|84.72|72.26|80.10|fastText |https://github.com/UniversalDependencies/UD_Slovak-SNK/blob/r2.7/LICENSE.txt | -|UD_Slovenian-SSJ |[slovenian-ud27](http://mozart.ipipan.waw.pl/~mklimaszewski/models/slovenian-ud27.tar.gz) |98.12|94.85 |95.18 |94.00 |97.79 |91.90|90.03|87.33|81.47|85.06|fastText |https://github.com/UniversalDependencies/UD_Slovenian-SSJ/blob/r2.7/LICENSE.txt | -|UD_Spanish-AnCora |[spanish-ud27](http://mozart.ipipan.waw.pl/~mklimaszewski/models/spanish-ud27.tar.gz) |98.83|98.72 |98.56 |97.88 |99.34 |92.38|90.12|86.13|83.81|85.55|fastText |https://github.com/UniversalDependencies/UD_Spanish-AnCora/blob/r2.7/LICENSE.txt | -|UD_Swedish-LinES |[swedish-ud27](http://mozart.ipipan.waw.pl/~mklimaszewski/models/swedish-ud27.tar.gz) |96.28|93.23 |89.17 |85.43 |96.86 |87.38|83.05|79.42|65.18|76.39|fastText |https://github.com/UniversalDependencies/UD_Swedish-LinES/blob/r2.7/LICENSE.txt | -|UD_Telugu-MTG |[telugu-ud27](http://mozart.ipipan.waw.pl/~mklimaszewski/models/telugu-ud27.tar.gz) |91.82|100.00|100.00|91.82 |100.00|91.40|81.83|77.36|72.78|77.36|fastText |https://github.com/UniversalDependencies/UD_Telugu-MTG/blob/r2.7/LICENSE.txt | -|UD_Turkish-BOUN |[turkish-ud27](http://mozart.ipipan.waw.pl/~mklimaszewski/models/turkish-ud27.tar.gz) |90.35|91.01 |92.83 |84.29 |95.25 |78.12|70.91|68.32|55.74|64.25|fastText |https://github.com/UniversalDependencies/UD_Turkish-BOUN/blob/r2.7/LICENSE.txt | -|UD_Ukrainian-IU |[ukrainian-ud27](http://mozart.ipipan.waw.pl/~mklimaszewski/models/ukrainian-ud27.tar.gz) |96.24|91.09 |91.15 |89.47 |96.58 |86.11|82.76|78.86|69.72|75.78|fastText |https://github.com/UniversalDependencies/UD_Ukrainian-IU/blob/r2.7/LICENSE.txt | -|UD_Urdu-UDTB |[urdu-ud27](http://mozart.ipipan.waw.pl/~mklimaszewski/models/urdu-ud27.tar.gz) |93.51|91.46 |82.80 |78.06 |96.27 |86.76|80.65|74.35|54.93|70.82|fastText |https://github.com/UniversalDependencies/UD_Urdu-UDTB/blob/r2.7/LICENSE.txt | -|UD_Uyghur-UDT |[uyghur-ud27](http://mozart.ipipan.waw.pl/~mklimaszewski/models/uyghur-ud27.tar.gz) |86.47|89.22 |85.15 |73.81 |94.37 |76.10|63.67|56.90|40.30|52.76|fastText |https://github.com/UniversalDependencies/UD_Uyghur-UDT/blob/r2.7/LICENSE.txt | -|UD_Vietnamese-VTB |[vietnamese-ud27](http://mozart.ipipan.waw.pl/~mklimaszewski/models/vietnamese-ud27.tar.gz) |86.64|82.09 |99.35 |81.51 |99.87 |66.19|56.65|53.44|47.44|53.35|fastText |https://github.com/UniversalDependencies/UD_Vietnamese-VTB/blob/r2.7/LICENSE.txt | +|Treebank | Model name |UPOS |XPOS |UFeats|AllTags|Lemmas|UAS |LAS |CLAS |MLAS |BLEX | Language model |LICENSE | +|-------------------------|--------------------------------------------------------------------------------------------------------------|-----|------|------|-------|------|-----|-----|-----|-----|-----|--------------------|---------------------------------------------------------------------------------------| +|UD_English-EWT | [english-bert-base-ud29](http://s3.clarin-pl.eu/models/combo/ud_29/english-bert-base-ud29.tar.gz) |96.58|96.24|97.17|94.65|97.18|91.7|89.4|87.01|82.03|83.84| bert-base-cased |https://github.com/UniversalDependencies/UD_English-EWT/blob/r2.9/LICENSE.txt| +|UD_Polish_PDB| [polish-herbert-base-ud29](http://s3.clarin-pl.eu/models/combo/ud_29/polish-herbert-base-ud29.tar.gz) |98.96|96.4|96.67|95.64|98|95.75|94.05|92.55|87.65|90.01| herbert-base |https://github.com/UniversalDependencies/UD_Polish_PDB/blob/r2.9/LICENSE.txt| +|UD_Polish_PDB| [polish-herbert-large-ud29](http://s3.clarin-pl.eu/models/combo/ud_29/polish-herbert-large-ud29.tar.gz) |99.01|96.53|96.92|95.92|98.1|95.62|93.93|92.39|87.77|90.01| herbert-large |https://github.com/UniversalDependencies/UD_Polish_PDB/blob/r2.9/LICENSE.txt| +|UD_Turkish-Kenet| [turkish-kenet-ud29](http://s3.clarin-pl.eu/models/combo/ud_29/turkish-kenet-ud29.tar.gz) |92.75|100|88.65|87.5|92.88|81.82|66.94|65.89|55.35|60.72| fastText |https://github.com/UniversalDependencies/UD_Turkish-Kenet/blob/r2.9/LICENSE.txt| +|UD_Icelandic-IcePaHC| [icelandic-icepahc-ud29](http://s3.clarin-pl.eu/models/combo/ud_29/icelandic-icepahc-ud29.tar.gz) |96.32|92.1|90.56|85.29|95.56|86.98|82.83|77.58|64.84|73.64| fastText |https://github.com/UniversalDependencies/UD_Icelandic-IcePaHC/blob/r2.9/LICENSE.txt| +|UD_Dutch-LassySmall| [dutch-lassysmall-ud29](http://s3.clarin-pl.eu/models/combo/ud_29/dutch-lassysmall-ud29.tar.gz) |95.66|93.78|95.48|92.64|89.75|89.37|85.25|80.6|74.4|67.45| fastText |https://github.com/UniversalDependencies/UD_Dutch-LassySmall/blob/r2.9/LICENSE.txt| +|UD_Bulgarian-BTB| [bulgarian-ud29](http://s3.clarin-pl.eu/models/combo/ud_29/bulgarian-ud29.tar.gz) |98.93|95.61|97.53|95.06|97.51|93.2|89.93|86.58|82.97|83.44| fastText |https://github.com/UniversalDependencies/UD_Bulgarian-BTB/blob/r2.9/LICENSE.txt| +|UD_Czech-CLTT| [czech-cltt-ud29](http://s3.clarin-pl.eu/models/combo/ud_29/czech-cltt-ud29.tar.gz) |98.74|89.51|89.34|88.01|95.11|86.33|83.38|80.06|69.3|75.57| fastText |https://github.com/UniversalDependencies/UD_Czech-CLTT/blob/r2.9/LICENSE.txt| +|UD_Serbian-SET| [serbian-ud29](http://s3.clarin-pl.eu/models/combo/ud_29/serbian-ud29.tar.gz) |97.86|93.14|93.31|92.49|96.64|89.9|86.66|84.03|75.91|80.65| fastText |https://github.com/UniversalDependencies/UD_Serbian-SET/blob/r2.9/LICENSE.txt| +|UD_Russian-Taiga| [russian-taiga-ud29](http://s3.clarin-pl.eu/models/combo/ud_29/russian-taiga-ud29.tar.gz) |96.2|100|93.22|91.76|94.73|81.83|77.55|74.74|67.06|69.91| fastText |https://github.com/UniversalDependencies/UD_Russian-Taiga/blob/r2.9/LICENSE.txt| +|UD_Belarusian-HSE| [belarusian-ud29](http://s3.clarin-pl.eu/models/combo/ud_29/belarusian-ud29.tar.gz) |98.17|96.11|93.71|91.37|95.78|87.24|84.58|81.47|74.22|77| fastText |https://github.com/UniversalDependencies/UD_Belarusian-HSE/blob/r2.9/LICENSE.txt| +|UD_Indonesian-GSD| [indonesian-ud29](http://s3.clarin-pl.eu/models/combo/ud_29/indonesian-ud29.tar.gz) |94.45|91.18|95.87|86.15|97.65|86.93|80.38|76.36|70.21|74.31| fastText |https://github.com/UniversalDependencies/UD_Indonesian-GSD/blob/r2.9/LICENSE.txt| +|UD_Norwegian-NynorskLIA| [norwegian-nynorsklia-ud29](http://s3.clarin-pl.eu/models/combo/ud_29/norwegian-nynorsklia-ud29.tar.gz) |93.53|100|92.03|89.47|96.68|76.72|70.75|65.36|57.09|62.72| fastText |https://github.com/UniversalDependencies/UD_Norwegian-NynorskLIA/blob/r2.9/LICENSE.txt| +|UD_Romanian-SiMoNERo| [romanian-simonero-ud29](http://s3.clarin-pl.eu/models/combo/ud_29/romanian-simonero-ud29.tar.gz) |97.91|96.85|96.27|95.89|98.92|93.35|91.09|87.88|82.48|86.75| fastText |https://github.com/UniversalDependencies/UD_Romanian-SiMoNERo/blob/r2.9/LICENSE.txt| +|UD_Afrikaans-AfriBooms| [afrikaans-ud29](http://s3.clarin-pl.eu/models/combo/ud_29/afrikaans-ud29.tar.gz) |96.7|90.57|96.37|90.02|97|87|83.33|76.83|71.14|73.02| fastText |https://github.com/UniversalDependencies/UD_Afrikaans-AfriBooms/blob/r2.9/LICENSE.txt| +|UD_Armenian-ArmTDP| [armenian-ud29](http://s3.clarin-pl.eu/models/combo/ud_29/armenian-ud29.tar.gz) |94.08|100|87.92|85.75|93.83|83.41|77.14|71.17|58.72|66.62| fastText |https://github.com/UniversalDependencies/UD_Armenian-ArmTDP/blob/r2.9/LICENSE.txt| +|UD_Catalan-AnCora| [catalan-ud29](http://s3.clarin-pl.eu/models/combo/ud_29/catalan-ud29.tar.gz) |98.83|96.18|98.47|95.82|99.3|93.53|91.29|86.69|84.06|86.1| fastText |https://github.com/UniversalDependencies/UD_Catalan-AnCora/blob/r2.9/LICENSE.txt| +|UD_Czech-PDT| [czech-pdt-ud29](http://s3.clarin-pl.eu/models/combo/ud_29/czech-pdt-ud29.tar.gz) |98.98|96.44|96.63|95.61|98.59|93.44|91.54|90.04|85.97|88.56| fastText |https://github.com/UniversalDependencies/UD_Czech-PDT/blob/r2.9/LICENSE.txt| +|UD_Swedish-LinES| [swedish-lines-ud29](http://s3.clarin-pl.eu/models/combo/ud_29/swedish-lines-ud29.tar.gz) |96.26|93.08|89.19|85.54|96.93|87.58|83.26|79.8|65.9|76.74| fastText |https://github.com/UniversalDependencies/UD_Swedish-LinES/blob/r2.9/LICENSE.txt| +|UD_French-Sequoia| [french-sequoia-ud29](http://s3.clarin-pl.eu/models/combo/ud_29/french-sequoia-ud29.tar.gz) |97.75|100|100|97.75|98.36|90.84|88.56|84.39|82.27|82.6| fastText |https://github.com/UniversalDependencies/UD_French-Sequoia/blob/r2.9/LICENSE.txt| +|UD_Turkish-Tourism| [turkish-tourism-ud29](http://s3.clarin-pl.eu/models/combo/ud_29/turkish-tourism-ud29.tar.gz) |98.39|100|94.47|94.11|98.9|95.61|89.46|86.63|79.02|85.64| fastText |https://github.com/UniversalDependencies/UD_Turkish-Tourism/blob/r2.9/LICENSE.txt| +|UD_Latin-UDante| [latin-udante-ud29](http://s3.clarin-pl.eu/models/combo/ud_29/latin-udante-ud29.tar.gz) |86.59|65.23|71.34|61.08|83.82|65.28|54.53|44.94|27.36|37.31| fastText |https://github.com/UniversalDependencies/UD_Latin-UDante/blob/r2.9/LICENSE.txt| +|UD_Chinese-GSD| [chinese-gsd-ud29](http://s3.clarin-pl.eu/models/combo/ud_29/chinese-gsd-ud29.tar.gz) |94.73|94.56|99.1|93.58|98.87|83.2|79.25|77.76|72.24|76.5| fastText |https://github.com/UniversalDependencies/UD_Chinese-GSD/blob/r2.9/LICENSE.txt| +|UD_Polish-LFG| [polish-lfg-ud29](http://s3.clarin-pl.eu/models/combo/ud_29/polish-lfg-ud29.tar.gz) |98.01|93.84|94.93|92.66|97.32|95.9|93.85|92.02|85.49|89.18| fastText |https://github.com/UniversalDependencies/UD_Polish-LFG/blob/r2.9/LICENSE.txt| +|UD_Turkish-IMST| [turkish-imst-ud29](http://s3.clarin-pl.eu/models/combo/ud_29/turkish-imst-ud29.tar.gz) |92.49|91.85|88.47|84.27|96.41|73.34|65.76|61.04|50.37|59.29| fastText |https://github.com/UniversalDependencies/UD_Turkish-IMST/blob/r2.9/LICENSE.txt| +|UD_Latin-LLCT| [latin-llct-ud29](http://s3.clarin-pl.eu/models/combo/ud_29/latin-llct-ud29.tar.gz) |99.46|96.9|96.84|96.39|97.22|95.55|94.55|93.67|89.55|90.31| fastText |https://github.com/UniversalDependencies/UD_Latin-LLCT/blob/r2.9/LICENSE.txt| +|UD_Norwegian-Bokmaal| [norwegian-bokmaal-ud29](http://s3.clarin-pl.eu/models/combo/ud_29/norwegian-bokmaal-ud29.tar.gz) |97.38|100|96.25|95.43|98.02|92.08|89.99|87.4|82.1|84.96| fastText |https://github.com/UniversalDependencies/UD_Norwegian-Bokmaal/blob/r2.9/LICENSE.txt| +|UD_Italian-ISDT| [italian-isdt-ud29](http://s3.clarin-pl.eu/models/combo/ud_29/italian-isdt-ud29.tar.gz) |98.09|97.95|100|97.84|98.2|92.91|90.9|86.61|84.5|84.42| fastText |https://github.com/UniversalDependencies/UD_Italian-ISDT/blob/r2.9/LICENSE.txt| +|UD_Danish-DDT| [danish-ud29](http://s3.clarin-pl.eu/models/combo/ud_29/danish-ud29.tar.gz) |96.8|100|95.99|94.89|97.14|85.61|82.84|79.63|73.1|76.78| fastText |https://github.com/UniversalDependencies/UD_Danish-DDT/blob/r2.9/LICENSE.txt| +|UD_Spanish-GSD| [spanish-gsd-ud29](http://s3.clarin-pl.eu/models/combo/ud_29/spanish-gsd-ud29.tar.gz) |96.17|100|96.77|94.22|98.61|90.27|87.22|81.89|74.02|80.23| fastText |https://github.com/UniversalDependencies/UD_Spanish-GSD/blob/r2.9/LICENSE.txt| +|UD_Persian-Seraji| [persian-seraji-ud29](http://s3.clarin-pl.eu/models/combo/ud_29/persian-seraji-ud29.tar.gz) |97.62|97.5|97.45|96.95|95.64|89.78|86.12|82.91|80.57|78.52| fastText |https://github.com/UniversalDependencies/UD_Persian-Seraji/blob/r2.9/LICENSE.txt| +|UD_Turkish-Atis| [turkish-atis-ud29](http://s3.clarin-pl.eu/models/combo/ud_29/turkish-atis-ud29.tar.gz) |98.09|100|97.59|97.2|98.63|89.94|87.51|87.02|84.88|86.18| fastText |https://github.com/UniversalDependencies/UD_Turkish-Atis/blob/r2.9/LICENSE.txt| +|UD_Italian-PoSTWITA| [italian-postwita-ud29](http://s3.clarin-pl.eu/models/combo/ud_29/italian-postwita-ud29.tar.gz) |95.39|95.06|95.71|93.03|96.49|84.9|79.6|74.38|68.51|71.57| fastText |https://github.com/UniversalDependencies/UD_Italian-PoSTWITA/blob/r2.9/LICENSE.txt| +|UD_Icelandic-Modern| [icelandic-modern-ud29](http://s3.clarin-pl.eu/models/combo/ud_29/icelandic-modern-ud29.tar.gz) |98.98|97.43|98.02|97.19|98.73|94.31|92.75|90.97|88.74|89.83| fastText |https://github.com/UniversalDependencies/UD_Icelandic-Modern/blob/r2.9/LICENSE.txt| +|UD_Basque-BDT| [basque-ud29](http://s3.clarin-pl.eu/models/combo/ud_29/basque-ud29.tar.gz) |94.58|100|91.42|88.58|95.6|84.64|80.61|79|68.55|75.24| fastText |https://github.com/UniversalDependencies/UD_Basque-BDT/blob/r2.9/LICENSE.txt| +|UD_Latvian-LVTB| [latvian-ud29](http://s3.clarin-pl.eu/models/combo/ud_29/latvian-ud29.tar.gz) |96.32|86.82|93.33|86.03|95.45|87.88|84.39|81.92|73.51|77.76| fastText |https://github.com/UniversalDependencies/UD_Latvian-LVTB/blob/r2.9/LICENSE.txt| +|UD_English-GUM| [english-gum-ud29](http://s3.clarin-pl.eu/models/combo/ud_29/english-gum-ud29.tar.gz) |96.31|96.02|97.04|94.74|97.69|89|86.15|81.61|76.59|78.64| fastText |https://github.com/UniversalDependencies/UD_English-GUM/blob/r2.9/LICENSE.txt| +|UD_Welsh-CCG| [welsh-ud29](http://s3.clarin-pl.eu/models/combo/ud_29/welsh-ud29.tar.gz) |92.58|90.77|86.14|82.55|89.72|83.37|75.6|68.95|53.54|58.95| fastText |https://github.com/UniversalDependencies/UD_Welsh-CCG/blob/r2.9/LICENSE.txt| +|UD_Russian-GSD| [russian-gsd-ud29](http://s3.clarin-pl.eu/models/combo/ud_29/russian-gsd-ud29.tar.gz) |97.02|96.48|91.72|90.27|95.7|87.47|83.43|81.47|72.15|77.4| fastText |https://github.com/UniversalDependencies/UD_Russian-GSD/blob/r2.9/LICENSE.txt| +|UD_Finnish-TDT| [finnish-tdt-ud29](http://s3.clarin-pl.eu/models/combo/ud_29/finnish-tdt-ud29.tar.gz) |96.41|97.97|94.01|92.55|88.29|89.27|86.46|84.61|77.32|71.77| fastText |https://github.com/UniversalDependencies/UD_Finnish-TDT/blob/r2.9/LICENSE.txt| +|UD_Norwegian-Nynorsk| [norwegian-nynorsk-ud29](http://s3.clarin-pl.eu/models/combo/ud_29/norwegian-nynorsk-ud29.tar.gz) |97.22|100|95.29|94.31|97.38|91.76|89.51|87.13|80.26|83.93| fastText |https://github.com/UniversalDependencies/UD_Norwegian-Nynorsk/blob/r2.9/LICENSE.txt| +|UD_Irish-IDT| [irish-ud29](http://s3.clarin-pl.eu/models/combo/ud_29/irish-ud29.tar.gz) |94.01|93.71|88.33|84.39|93.53|85.57|79.24|73.83|59.54|67.72| fastText |https://github.com/UniversalDependencies/UD_Irish-IDT/blob/r2.9/LICENSE.txt| +|UD_Urdu-UDTB| [urdu-ud29](http://s3.clarin-pl.eu/models/combo/ud_29/urdu-ud29.tar.gz) |93.6|91.66|82.84|78.25|96.1|86.58|80.76|74.62|54.91|70.95| fastText |https://github.com/UniversalDependencies/UD_Urdu-UDTB/blob/r2.9/LICENSE.txt| +|UD_Portuguese-Bosque| [portuguese-bosque-ud29](http://s3.clarin-pl.eu/models/combo/ud_29/portuguese-bosque-ud29.tar.gz) |97.4|100|96.3|94.95|98.21|91.06|87.92|82.65|76.02|80.44| fastText |https://github.com/UniversalDependencies/UD_Portuguese-Bosque/blob/r2.9/LICENSE.txt| +|UD_Spanish-AnCora| [spanish-ancora-ud29](http://s3.clarin-pl.eu/models/combo/ud_29/spanish-ancora-ud29.tar.gz) |98.83|95.97|98.57|95.4|99.34|92.38|90.09|85.84|83.37|85.23| fastText |https://github.com/UniversalDependencies/UD_Spanish-AnCora/blob/r2.9/LICENSE.txt| +|UD_Czech-FicTree| [czech-fictree-ud29](http://s3.clarin-pl.eu/models/combo/ud_29/czech-fictree-ud29.tar.gz) |98.03|93.98|95.37|93.01|98.26|92.5|90.06|87.28|80.76|85.2| fastText |https://github.com/UniversalDependencies/UD_Czech-FicTree/blob/r2.9/LICENSE.txt| +|UD_Italian-VIT| [italian-vit-ud29](http://s3.clarin-pl.eu/models/combo/ud_29/italian-vit-ud29.tar.gz) |97.64|96.91|97.34|95.64|98.41|89.73|86.15|80.57|76.01|78.86| fastText |https://github.com/UniversalDependencies/UD_Italian-VIT/blob/r2.9/LICENSE.txt| +|UD_Dutch-Alpino| [dutch-alpino-ud29](http://s3.clarin-pl.eu/models/combo/ud_29/dutch-alpino-ud29.tar.gz) |96.37|94.28|96.48|93.5|89.09|91.45|88|82.53|76.73|67.01| fastText |https://github.com/UniversalDependencies/UD_Dutch-Alpino/blob/r2.9/LICENSE.txt| +|UD_Hindi-HDTB| [hindi-ud29](http://s3.clarin-pl.eu/models/combo/ud_29/hindi-ud29.tar.gz) |97.05|96.59|93.92|91.5|98.83|94.58|91.24|87.49|77.22|86.19| fastText |https://github.com/UniversalDependencies/UD_Hindi-HDTB/blob/r2.9/LICENSE.txt| +|UD_Persian-PerDT| [persian-perdt-ud29](http://s3.clarin-pl.eu/models/combo/ud_29/persian-perdt-ud29.tar.gz) |97.31|97.22|97.78|95.23|98.89|93.3|90.9|89|85|87.8| fastText |https://github.com/UniversalDependencies/UD_Persian-PerDT/blob/r2.9/LICENSE.txt| +|UD_Japanese-GSD| [japanese-gsd-ud29](http://s3.clarin-pl.eu/models/combo/ud_29/japanese-gsd-ud29.tar.gz) |98.29|96.88|100|96.51|98.9|94.05|92.73|88.76|86.52|87.53| fastText |https://github.com/UniversalDependencies/UD_Japanese-GSD/blob/r2.9/LICENSE.txt| +|UD_German-GSD| [german-gsd-ud29](http://s3.clarin-pl.eu/models/combo/ud_29/german-gsd-ud29.tar.gz) |94.15|96.5|90|84.5|96.38|86.53|81.63|77.2|59.57|72.5| fastText |https://github.com/UniversalDependencies/UD_German-GSD/blob/r2.9/LICENSE.txt| +|UD_Slovak-SNK| [slovak-ud29](http://s3.clarin-pl.eu/models/combo/ud_29/slovak-ud29.tar.gz) |95.24|86.04|89.75|84.73|94.86|90.08|87.15|85.16|72.59|79.93| fastText |https://github.com/UniversalDependencies/UD_Slovak-SNK/blob/r2.9/LICENSE.txt| +|UD_Uyghur-UDT| [uyghur-ud29](http://s3.clarin-pl.eu/models/combo/ud_29/uyghur-ud29.tar.gz) |86.11|88.5|84.47|72.88|94.33|74.94|61.66|54.07|38.58|50.33| fastText |https://github.com/UniversalDependencies/UD_Uyghur-UDT/blob/r2.9/LICENSE.txt| +|UD_Slovenian-SSJ| [slovenian-ud29](http://s3.clarin-pl.eu/models/combo/ud_29/slovenian-ud29.tar.gz) |98.12|94.74|95.11|93.95|97.96|92.28|90.44|87.81|82|85.84| fastText |https://github.com/UniversalDependencies/UD_Slovenian-SSJ/blob/r2.9/LICENSE.txt| +|UD_Turkish-Penn| [turkish-penn-ud29](http://s3.clarin-pl.eu/models/combo/ud_29/turkish-penn-ud29.tar.gz) |95.64|100|93.02|91.92|93.82|83.96|69.96|66.62|58.07|61.81| fastText |https://github.com/UniversalDependencies/UD_Turkish-Penn/blob/r2.9/LICENSE.txt| +|UD_Galician-CTG| [galician-ud29](http://s3.clarin-pl.eu/models/combo/ud_29/galician-ud29.tar.gz) |97.27|95.83|100|95.53|98.3|85.82|82.78|77.39|70.62|75.79| fastText |https://github.com/UniversalDependencies/UD_Galician-CTG/blob/r2.9/LICENSE.txt| +|UD_Czech-CAC| [czech-cac-ud29](http://s3.clarin-pl.eu/models/combo/ud_29/czech-cac-ud29.tar.gz) |99.04|95.49|95.47|94.47|97.74|92.39|90.25|88.36|83.05|85.91| fastText |https://github.com/UniversalDependencies/UD_Czech-CAC/blob/r2.9/LICENSE.txt| +|UD_Finnish-FTB| [finnish-ftb-ud29](http://s3.clarin-pl.eu/models/combo/ud_29/finnish-ftb-ud29.tar.gz) |94.55|92.55|94.39|91.16|95.16|89.65|86.33|83.38|77.1|80.03| fastText |https://github.com/UniversalDependencies/UD_Finnish-FTB/blob/r2.9/LICENSE.txt| +|UD_Latin-ITTB| [latin-ittb-ud29](http://s3.clarin-pl.eu/models/combo/ud_29/latin-ittb-ud29.tar.gz) |98.77|94.21|96.51|92.8|99.18|91.26|89.14|86.78|81.86|86.31| fastText |https://github.com/UniversalDependencies/UD_Latin-ITTB/blob/r2.9/LICENSE.txt| +|UD_Russian-SynTagRus| [russian-syntagrus-ud29](http://s3.clarin-pl.eu/models/combo/ud_29/russian-syntagrus-ud29.tar.gz) |98.39|100|93.24|92.83|97.93|93.55|90.94|89.5|80.49|87.16| fastText |https://github.com/UniversalDependencies/UD_Russian-SynTagRus/blob/r2.9/LICENSE.txt| +|UD_Greek-GDT| [greek-ud29](http://s3.clarin-pl.eu/models/combo/ud_29/greek-ud29.tar.gz) |97.31|97.34|93.68|92.82|95.51|91.01|88.55|83.71|75.08|77.83| fastText |https://github.com/UniversalDependencies/UD_Greek-GDT/blob/r2.9/LICENSE.txt| +|UD_Turkish-BOUN| [turkish-boun-ud29](http://s3.clarin-pl.eu/models/combo/ud_29/turkish-boun-ud29.tar.gz) |90.29|90.77|91.48|84.19|95.27|77.93|70.78|68.21|55.56|64.27| fastText |https://github.com/UniversalDependencies/UD_Turkish-BOUN/blob/r2.9/LICENSE.txt| +|UD_Vietnamese-VTB| [vietnamese-ud29](http://s3.clarin-pl.eu/models/combo/ud_29/vietnamese-ud29.tar.gz) |86.75|81.94|99.41|81.52|99.87|66.32|56.8|54.07|48.5|53.99| fastText |https://github.com/UniversalDependencies/UD_Vietnamese-VTB/blob/r2.9/LICENSE.txt| +|UD_Romanian-RRT| [romanian-rrt-ud29](http://s3.clarin-pl.eu/models/combo/ud_29/romanian-rrt-ud29.tar.gz) |97.77|96.73|96.96|96.34|97.95|90.61|86.52|82.75|78.43|80.99| fastText |https://github.com/UniversalDependencies/UD_Romanian-RRT/blob/r2.9/LICENSE.txt| +|UD_Japanese-GSDLUW| [japanese-gsdluw-ud29](http://s3.clarin-pl.eu/models/combo/ud_29/japanese-gsdluw-ud29.tar.gz) |97.86|96.58|100|96.43|95.72|94.29|93.01|86.51|83.15|79.3| fastText |https://github.com/UniversalDependencies/UD_Japanese-GSDLUW/blob/r2.9/LICENSE.txt| +|UD_English-LinES| [english-lines-ud29](http://s3.clarin-pl.eu/models/combo/ud_29/english-lines-ud29.tar.gz) |96.27|95.47|95.67|92.19|97.91|86.69|82.68|78.29|71.58|76.1| fastText |https://github.com/UniversalDependencies/UD_English-LinES/blob/r2.9/LICENSE.txt| +|UD_Polish-PDB| [polish-pdb-ud29](http://s3.clarin-pl.eu/models/combo/ud_29/polish-pdb-ud29.tar.gz) |98.33|94.37|94.62|93.34|97.55|92.97|90.55|88.24|81.56|85.71| fastText |https://github.com/UniversalDependencies/UD_Polish-PDB/blob/r2.9/LICENSE.txt| +|UD_Telugu-MTG| [telugu-ud29](http://s3.clarin-pl.eu/models/combo/ud_29/telugu-ud29.tar.gz) |91.96|92.37|100|91.82|100|91.54|82.11|77.78|73.18|77.78| fastText |https://github.com/UniversalDependencies/UD_Telugu-MTG/blob/r2.9/LICENSE.txt| +|UD_English-Atis| [english-atis-ud29](http://s3.clarin-pl.eu/models/combo/ud_29/english-atis-ud29.tar.gz) |98.51|100|97.83|97.2|99.91|94.59|92.33|90.05|85.7|89.98| fastText |https://github.com/UniversalDependencies/UD_English-Atis/blob/r2.9/LICENSE.txt| +|UD_Hungarian-Szeged| [hungarian-ud29](http://s3.clarin-pl.eu/models/combo/ud_29/hungarian-ud29.tar.gz) |92.42|100|88.06|85.29|92.42|80.81|75.26|73.18|57.65|66| fastText |https://github.com/UniversalDependencies/UD_Hungarian-Szeged/blob/r2.9/LICENSE.txt| +|UD_French-Rhapsodie| [french-rhapsodie-ud29](http://s3.clarin-pl.eu/models/combo/ud_29/french-rhapsodie-ud29.tar.gz) |94.61|97.79|92.26|88.2|96.44|81.24|76.01|69.06|59.42|65.88| fastText |https://github.com/UniversalDependencies/UD_French-Rhapsodie/blob/r2.9/LICENSE.txt| +|UD_Swedish-Talbanken| [swedish-talbanken-ud29](http://s3.clarin-pl.eu/models/combo/ud_29/swedish-talbanken-ud29.tar.gz) |97.38|95.79|95.83|94.39|97.55|88.29|84.88|82.34|76.32|79.63| fastText |https://github.com/UniversalDependencies/UD_Swedish-Talbanken/blob/r2.9/LICENSE.txt| +|UD_Chinese-GSDSimp| [chinese-gsdsimp-ud29](http://s3.clarin-pl.eu/models/combo/ud_29/chinese-gsdsimp-ud29.tar.gz) |94.54|94.39|99.13|93.29|98.98|82.77|78.57|77.07|71.55|75.89| fastText |https://github.com/UniversalDependencies/UD_Chinese-GSDSimp/blob/r2.9/LICENSE.txt| +|UD_Estonian-EDT| [estonian-edt-ud29](http://s3.clarin-pl.eu/models/combo/ud_29/estonian-edt-ud29.tar.gz) |97.06|97.93|95.38|93.91|85.22|87.75|84.68|82.93|77.25|65.94| fastText |https://github.com/UniversalDependencies/UD_Estonian-EDT/blob/r2.9/LICENSE.txt| +|UD_Italian-TWITTIRO| [italian-twittiro-ud29](http://s3.clarin-pl.eu/models/combo/ud_29/italian-twittiro-ud29.tar.gz) |92.24|91.16|90.49|86.16|92.37|79.77|73.39|65.18|54.05|57.76| fastText |https://github.com/UniversalDependencies/UD_Italian-TWITTIRO/blob/r2.9/LICENSE.txt| +|UD_Portuguese-GSD| [portuguese-gsd-ud29](http://s3.clarin-pl.eu/models/combo/ud_29/portuguese-gsd-ud29.tar.gz) |98.01|98|99.88|97.91|99.14|92.84|91.3|87.07|84.91|86.15| fastText |https://github.com/UniversalDependencies/UD_Portuguese-GSD/blob/r2.9/LICENSE.txt| +|UD_Romanian-Nonstandard| [romanian-nonstandard-ud29](http://s3.clarin-pl.eu/models/combo/ud_29/romanian-nonstandard-ud29.tar.gz) |97.1|92.51|90.87|89.45|95.59|90.53|86.44|82.19|69.15|77.48| fastText |https://github.com/UniversalDependencies/UD_Romanian-Nonstandard/blob/r2.9/LICENSE.txt| +|UD_Italian-ParTUT| [italian-partut-ud29](http://s3.clarin-pl.eu/models/combo/ud_29/italian-partut-ud29.tar.gz) |97.77|97.64|97.2|96.29|97.69|91.24|88.93|82.65|78.75|80.09| fastText |https://github.com/UniversalDependencies/UD_Italian-ParTUT/blob/r2.9/LICENSE.txt| +|UD_English-ParTUT| [english-partut-ud29](http://s3.clarin-pl.eu/models/combo/ud_29/english-partut-ud29.tar.gz) |96.01|95.72|95.33|93.66|97.51|88.41|85.56|80.54|73.66|78.23| fastText |https://github.com/UniversalDependencies/UD_English-ParTUT/blob/r2.9/LICENSE.txt| +|UD_Maltese-MUDT| [maltese-ud29](http://s3.clarin-pl.eu/models/combo/ud_29/maltese-ud29.tar.gz) |93.02|91.68|100|91.02|100|81.13|74.82|65.6|59.4|65.6| fastText |https://github.com/UniversalDependencies/UD_Maltese-MUDT/blob/r2.9/LICENSE.txt| +|UD_English-EWT| [english-ewt-ud29](http://s3.clarin-pl.eu/models/combo/ud_29/english-ewt-ud29.tar.gz) |95.76|95.37|96.48|93.43|96.96|89.25|86.43|83.3|77.53|80.17| fastText |https://github.com/UniversalDependencies/UD_English-EWT/blob/r2.9/LICENSE.txt| +|UD_Estonian-EWT| [estonian-ewt-ud29](http://s3.clarin-pl.eu/models/combo/ud_29/estonian-ewt-ud29.tar.gz) |91.16|94.05|88.09|84.48|82.93|76.86|70.4|66.36|55.58|52.79| fastText |https://github.com/UniversalDependencies/UD_Estonian-EWT/blob/r2.9/LICENSE.txt| +|UD_Lithuanian-ALKSNIS| [lithuanian-alksnis-ud29](http://s3.clarin-pl.eu/models/combo/ud_29/lithuanian-alksnis-ud29.tar.gz) |93.16|86.49|88.35|84.77|91.74|78.34|73.17|70.62|60.75|64.71| fastText |https://github.com/UniversalDependencies/UD_Lithuanian-ALKSNIS/blob/r2.9/LICENSE.txt| +|UD_Hebrew-HTB| [hebrew-htb-ud29](http://s3.clarin-pl.eu/models/combo/ud_29/hebrew-htb-ud29.tar.gz) |96.84|96.83|95.42|94.45|96.15|89.91|86.93|80.92|74.15|75.98| fastText |https://github.com/UniversalDependencies/UD_Hebrew-HTB/blob/r2.9/LICENSE.txt| +|UD_Latin-PROIEL| [latin-proiel-ud29](http://s3.clarin-pl.eu/models/combo/ud_29/latin-proiel-ud29.tar.gz) |95.98|96.13|89.22|88|95.95|81.95|76.74|73.69|63.49|71.56| fastText |https://github.com/UniversalDependencies/UD_Latin-PROIEL/blob/r2.9/LICENSE.txt| +|UD_French-GSD| [french-gsd-ud29](http://s3.clarin-pl.eu/models/combo/ud_29/french-gsd-ud29.tar.gz) |97.86|100|97.98|97.03|98.41|92.6|90.36|86.08|82.51|84.19| fastText |https://github.com/UniversalDependencies/UD_French-GSD/blob/r2.9/LICENSE.txt| +|UD_Ukrainian-IU| [ukrainian-ud29](http://s3.clarin-pl.eu/models/combo/ud_29/ukrainian-ud29.tar.gz) |96.09|91.07|91.2|89.47|96.54|85.8|82.35|78.71|69.97|75.88| fastText |https://github.com/UniversalDependencies/UD_Ukrainian-IU/blob/r2.9/LICENSE.txt| +|UD_Croatian-SET| [croatian-ud29](http://s3.clarin-pl.eu/models/combo/ud_29/croatian-ud29.tar.gz) |97.83|94|94.57|93.35|96.79|89.39|85.51|82.79|75.46|79.2| fastText |https://github.com/UniversalDependencies/UD_Croatian-SET/blob/r2.9/LICENSE.txt| +|UD_Arabic-PADT| [arabic-padt-ud29](http://s3.clarin-pl.eu/models/combo/ud_29/arabic-padt-ud29.tar.gz) |96.82|93.89|93.93|93.3|93.68|87.42|82.53|79.19|73.1|73.42| fastText |https://github.com/UniversalDependencies/UD_Arabic-PADT/blob/r2.9/LICENSE.txt| +|UD_Turkish-FrameNet| [turkish-framenet-ud29](http://s3.clarin-pl.eu/models/combo/ud_29/turkish-framenet-ud29.tar.gz) |94|100|90.12|88.82|93.8|91|80.37|77.04|66.76|71.35| fastText |https://github.com/UniversalDependencies/UD_Turkish-FrameNet/blob/r2.9/LICENSE.txt| +|UD_Tamil-TTB| [tamil-ud29](http://s3.clarin-pl.eu/models/combo/ud_29/tamil-ud29.tar.gz) |82.76|77.33|82.45|71.69|92.31|71.9|60.58|56.31|44.83|51.86| fastText |https://github.com/UniversalDependencies/UD_Tamil-TTB/blob/r2.9/LICENSE.txt| +|UD_French-ParTUT| [french-partut-ud29](http://s3.clarin-pl.eu/models/combo/ud_29/french-partut-ud29.tar.gz) |96.5|96|93.66|92.66|96.58|91.39|88.71|84.02|73.11|79.17| fastText |https://github.com/UniversalDependencies/UD_French-ParTUT/blob/r2.9/LICENSE.txt| +|UD_Scottish_Gaelic-ARCOSG| [scottish-gaelic-ud29](http://s3.clarin-pl.eu/models/combo/ud_29/scottish-gaelic-ud29.tar.gz) |95.27|89.46|91.8|87.94|95.23|85.92|81.11|75.86|66.46|71.11| fastText |https://github.com/UniversalDependencies/UD_Scottish_Gaelic-ARCOSG/blob/r2.9/LICENSE.txt| +|UD_Old_French-SRCMF| [old-french-ud29](http://s3.clarin-pl.eu/models/combo/ud_29/old-french-ud29.tar.gz) |95.53|95.33|97.12|94.2|100|89.76|85.37|82.38|77.57|82.38| fastText - French |https://github.com/UniversalDependencies/UD_Old_French-SRCMF/blob/r2.9/LICENSE.txt| +|UD_Ancient_Greek-Perseus| [ancient-greek-perseus-ud29](http://s3.clarin-pl.eu/models/combo/ud_29/ancient-greek-perseus-ud29.tar.gz) |90.17|80.42|87.09|78.93|83.8|76.96|70.29|63.75|46.19|49.43| fastText - Greek |https://github.com/UniversalDependencies/UD_Ancient_Greek-Perseus/blob/r2.9/LICENSE.txt| +|UD_Ancient_Greek-PROIEL| [ancient-greek-proiel-ud29](http://s3.clarin-pl.eu/models/combo/ud_29/ancient-greek-proiel-ud29.tar.gz) |97.42|97.56|90.99|89.79|95.6|85.56|81.06|76.31|65.19|72.3| fastText - Greek |https://github.com/UniversalDependencies/UD_Ancient_Greek-PROIEL/blob/r2.9/LICENSE.txt| +|UD_Western_Armenian-ArmTDP| [western-armenian-ud29](http://s3.clarin-pl.eu/models/combo/ud_29/western-armenian-ud29.tar.gz) |95.73|100|90.19|88.93|95.71|85.83|80.17|72.81|61.2|69.05| fastText - Armenian |https://github.com/UniversalDependencies/UD_Western_Armenian-ArmTDP/blob/r2.9/LICENSE.txt| +|UD_Classical_Chinese-Kyoto| [classical-chiense-kyoto-ud29](http://s3.clarin-pl.eu/models/combo/ud_29/classical-chiense-kyoto-ud29.tar.gz) |91.72|85.04|100|83.3|97.53|82.73|76.73|76|72.81|74.27| fastText - Chinese |https://github.com/UniversalDependencies/UD_Classical_Chinese-Kyoto/blob/r2.9/LICENSE.txt| +|UD_German-HDT| [german-hdt-ud29](http://s3.clarin-pl.eu/models/combo/ud_29/german-hdt-ud29.tar.gz) |98.45|98.40|93.57|93.14|93.43|97.00|95.96|93.65|83.41|83.73| fastText |https://github.com/UniversalDependencies/UD_German-HDT/blob/r2.9/LICENSE.txt| \ No newline at end of file diff --git a/docs/prediction.md b/docs/prediction.md index b359bdf..879f980 100644 --- a/docs/prediction.md +++ b/docs/prediction.md @@ -5,7 +5,7 @@ The pre-trained models can be automatically downloaded with the `from_pretrained ```python from combo.predict import COMBO -nlp = COMBO.from_pretrained(`polish-herbert-base`) +nlp = COMBO.from_pretrained("polish-herbert-base-ud29") sentence = nlp("Sentence to parse.") ``` -- GitLab