Number of results to display per page
Search Results
82. CorPipe 23 multilingual CorefUD 1.1 model (corpipe23-corefud1.1-231206)
- Creator:
- Straka, Milan
- Publisher:
- Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)
- Type:
- tool and toolService
- Subject:
- coreference resolution, CorPipe, and CorefUD
- Language:
- Catalan, Czech, German, English, Spanish, French, Hungarian, Lithuanian, Norwegian Bokmål, Norwegian Nynorsk, Polish, Russian, and Turkish
- Description:
- The `corpipe23-corefud1.1-231206` is a `mT5-large`-based multilingual model for coreference resolution usable in CorPipe 23 (https://github.com/ufal/crac2023-corpipe). It is released under the CC BY-NC-SA 4.0 license. The model is language agnostic (no _corpus id_ on input), so it can be used to predict coreference in any `mT5` language (for zero-shot evaluation, see the paper). However, note that the empty nodes must be present already on input, they are not predicted (the same settings as in the CRAC23 shared task).
- Rights:
- Creative Commons - Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0), http://creativecommons.org/licenses/by-nc-sa/4.0/, and PUB
83. CorPipe 23 multilingual CorefUD 1.2 model (corpipe23-corefud1.2-240906)
- Creator:
- Straka, Milan
- Publisher:
- Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)
- Type:
- tool and toolService
- Subject:
- coreference resolution, CorPipe, and CorefUD
- Language:
- Catalan, Czech, Church Slavic, German, English, Spanish, French, Ancient Greek (to 1453), Ancient Hebrew, Hungarian, Lithuanian, Norwegian Bokmål, Norwegian Nynorsk, Polish, Russian, and Turkish
- Description:
- The `corpipe23-corefud1.2-240906` is a `mT5-large`-based multilingual model for coreference resolution usable in CorPipe 23 <https://github.com/ufal/crac2023-corpipe>. It is released under the CC BY-NC-SA 4.0 license. The model is language agnostic (no corpus id on input), so it can be in theory used to predict coreference in any `mT5` language. However, the model expects empty nodes to be already present on input, predicted by the https://www.kaggle.com/models/ufal-mff/crac2024_zero_nodes_baseline/. This model was present in the CorPipe 24 paper as an alternative to a single-stage approach, where the empty nodes are predicted joinly with coreference resolution (via http://hdl.handle.net/11234/1-5672), an approach circa twice as fast but of slightly worse quality.
- Rights:
- Creative Commons - Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0), http://creativecommons.org/licenses/by-nc-sa/4.0/, and PUB
84. CorPipe 24 Multilingual CorefUD 1.2 Model (corpipe24-corefud1.2-240906)
- Creator:
- Straka, Milan
- Publisher:
- Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)
- Type:
- tool and toolService
- Subject:
- coreference resolution, CorPipe, and CorefUD
- Language:
- Catalan, Czech, German, English, Spanish, French, Hungarian, Lithuanian, Norwegian Bokmål, Norwegian Nynorsk, Polish, Russian, Turkish, Church Slavic, Ancient Greek (to 1453), and Ancient Hebrew
- Description:
- The `corpipe24-corefud1.2-240906` is a `mT5-large`-based multilingual model for coreference resolution usable in CorPipe 24 (https://github.com/ufal/crac2024-corpipe). It is released under the CC BY-NC-SA 4.0 license. The model is language agnostic (no corpus id on input), so it can be in theory used to predict coreference in any `mT5` language. This model jointly predicts also the empty nodes needed for zero coreference. The paper introducing this model also presents an alternative two-stage approach first predicting empty nodes (via https://www.kaggle.com/models/ufal-mff/crac2024_zero_nodes_baseline/) and then performing coreference resolution (via http://hdl.handle.net/11234/1-5673), which is circa twice as slow but slightly better.
- Rights:
- Creative Commons - Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0), http://creativecommons.org/licenses/by-nc-sa/4.0/, and PUB
85. Corpus for training and evaluating diacritics restoration systems
- Creator:
- Náplava, Jakub, Straka, Milan, Hajič, Jan, and Straňák, Pavel
- Publisher:
- Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)
- Type:
- text and corpus
- Subject:
- diacritical marks generation and natural language correction
- Language:
- Czech, Vietnamese, Romanian, Polish, Slovak, Spanish, Croatian, Irish, Latvian, Hungarian, French, and Turkish
- Description:
- Corpus of texts in 12 languages. For each language, we provide one training, one development and one testing set acquired from Wikipedia articles. Moreover, each language dataset contains (substantially larger) training set collected from (general) Web texts. All sets, except for Wikipedia and Web training sets that can contain similar sentences, are disjoint. Data are segmented into sentences which are further word tokenized. All data in the corpus contain diacritics. To strip diacritics from them, use Python script diacritization_stripping.py contained within attached stripping_diacritics.zip. This script has two modes. We generally recommend using method called uninames, which for some languages behaves better. The code for training recurrent neural-network based model for diacritics restoration is located at https://github.com/arahusky/diacritics_restoration.
- Rights:
- Creative Commons - Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0), http://creativecommons.org/licenses/by-nc-sa/4.0/, and PUB
86. CUBBITT Translation Models (en-fr) (v1.0)
- Creator:
- Popel, Martin, Tomková, Markéta, Tomek, Jakub, Kaiser, Łukasz, Uszkoreit, Jakob, Bojar, Ondřej, and Žabokrtský, Zdeněk
- Publisher:
- Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)
- Type:
- tool and toolService
- Subject:
- machine translation, neural machine translation, transformer, and cubbitt
- Language:
- English and French
- Description:
- CUBBITT En-Fr translation models, exported via TensorFlow Serving, available in the Lindat translation service (https://lindat.mff.cuni.cz/services/translation/). Models are compatible with Tensor2tensor version 1.6.6. For details about the model training (data, model hyper-parameters), please contact the archive maintainer. Evaluation on newstest2014 (BLEU): en->fr: 38.2 fr->en: 36.7 (Evaluated using multeval: https://github.com/jhclark/multeval)
- Rights:
- Creative Commons - Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0), http://creativecommons.org/licenses/by-nc-sa/4.0/, and PUB
87. Descartesova metoda ve vědách a ve filosofii
- Creator:
- Josef Beneš
- Publisher:
- Česká akademie věd a umění
- Format:
- print and xiv, 327 s.
- Type:
- text, volume, studie, model:monograph, and TEXT
- Subject:
- Moderní západní filozofie, Descartes, René, 1596-1650, filozofové, filozofické myšlení, filozofie vědy, vědecká metodologie, francouzská filozofie, 101-051, 14(44), 001.11, (049), 5, and 14(100-15)"15/20"
- Language:
- Czech, Latin, and French
- Description:
- napsal Josef Beneš., KČSN, Obsahuje bibliografii, and Část. latinský a francouzský text
- Rights:
- http://creativecommons.org/licenses/by-nc-sa/4.0/ and policy:public
88. Filosofický časopis
- Format:
- Type:
- model:supplement and TEXT
- Language:
- Czech, Latin, Slovak, and French
- Description:
- Obsah ročníku LXX (2022)
- Rights:
- http://creativecommons.org/licenses/by-nc-sa/4.0/ and policy:public
89. Filosofický časopis
- Type:
- model:periodicalitem and TEXT
- Language:
- Czech, English, Slovak, and French
- Description:
- 1
- Rights:
- http://creativecommons.org/licenses/by-nc-sa/4.0/ and policy:public
90. Inteligence květin
- Creator:
- Maeterlinck, Maurice and Zaorálek, Jaroslav
- Publisher:
- R. Škeřík
- Format:
- print, svazek, and 137 stran.
- Type:
- model:monograph and TEXT
- Subject:
- Metafyzika, filozofie přírody, květiny, 5, and 11
- Language:
- Czech and French
- Description:
- Maurice Maeterlinck., Přeloženo z francouzštiny, "Přeložil Jaroslav Zaorálek"--Tiráž, Kromě vydání na papíře "Antik" vydáno bylo 300 číslovaných výtisků na papíře "Japan Banzay", z nichž výtisky číslo 1-25 jsou M. Maeterlinckem podepsány, and Číslovaný výtisk 61
- Rights:
- http://creativecommons.org/licenses/by-nc-sa/4.0/ and policy:public