Number of results to display per page
Search Results
22. NameTag 2 Models (2020-08-31)
- Creator:
- Straková, Jana and Straka, Milan
- Publisher:
- Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)
- Type:
- text, mlmodel, and languageDescription
- Subject:
- named entity recognition
- Language:
- English, German, Dutch, Spanish, and Czech
- Description:
- NER models for NameTag 2, named entity recognition tool, for English, German, Dutch, Spanish and Czech. Model documentation including performance can be found here: https://ufal.mff.cuni.cz/nametag/2/models . These models are for NameTag 2, named entity recognition tool, which can be found here: https://ufal.mff.cuni.cz/nametag/2 .
- 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
23. NameTag 2 Models (2021-09-16)
- Creator:
- Straková, Jana and Straka, Milan
- Publisher:
- Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)
- Type:
- text, mlmodel, and languageDescription
- Subject:
- named entity recognition and NER
- Language:
- English, German, Dutch, Spanish, and Czech
- Description:
- NER models for NameTag 2, named entity recognition tool, for English, German, Dutch, Spanish and Czech. Model documentation including performance can be found here: https://ufal.mff.cuni.cz/nametag/2/models . These models are for NameTag 2, named entity recognition tool, which can be found here: https://ufal.mff.cuni.cz/nametag/2 .
- 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
24. NorGram
- Type:
- languageDescription
- Description:
- All central constructions; lexicon >80 000 lemmas, Lexical-Functional Grammar (LFG) and Minimal Recursion Semantics (MRS)
- Rights:
- Not specified
25. POS Tagging and Lemmatization (Czech model)
- Creator:
- Vysušilová, Petra and Straka, Milan
- Publisher:
- Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)
- Type:
- text, mlmodel, and languageDescription
- Subject:
- BERT, PoS tagging, and lemmatization
- Language:
- Czech
- Description:
- Model trained for Czech POS Tagging and Lemmatization using Czech version of BERT model, RobeCzech. Model is trained on data from Prague Dependency Treebank 3.5. Model is a part of Czech NLP with Contextualized Embeddings master thesis and presented a state-of-the-art performance on the date of submission of the work. Demo jupyter notebook is available on the project GitHub.
- 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
26. Processing of intraclausal garden-path structures in Czech
- Creator:
- Ceháková, Markéta and Chromý, Jan
- Publisher:
- Charles University, Faculty of Arts, Institute of Czech Language and Theory of Communication
- Type:
- text, other, and languageDescription
- Subject:
- psycholinguistic experiments, sentence processing, Czech, garden-path, reading comprehension, and syntax
- Language:
- Czech
- Description:
- Experimental materials, data and R scripts used in the paper "Garden-path sentences and the diversity of their (mis)representations" (Ceháková - Chromý, 2023).
- Rights:
- Creative Commons - Attribution 4.0 International (CC BY 4.0), http://creativecommons.org/licenses/by/4.0/, and PUB
27. Propädeutische Grammatik (ProGr@mm)
- Publisher:
- Institut für Deutsche Sprache
- Type:
- languageDescription
- Language:
- German
- Description:
- Web Information &Learning System, contains reusable e-learning resources, XML format
- Rights:
- Not specified
28. RobeCzech Base
- Creator:
- Straka, Milan, Náplava, Jakub, Straková, Jana, and Samuel, David
- Publisher:
- Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)
- Type:
- text, mlmodel, and languageDescription
- Subject:
- Czech, BERT, and RoBERTa
- Language:
- Czech
- Description:
- RobeCzech is a monolingual RoBERTa language representation model trained on Czech data. RoBERTa is a robustly optimized Transformer-based pretraining approach. We show that RobeCzech considerably outperforms equally-sized multilingual and Czech-trained contextualized language representation models, surpasses current state of the art in all five evaluated NLP tasks and reaches state-of-theart results in four of them. The RobeCzech model is released publicly at https://hdl.handle.net/11234/1-3691 and https://huggingface.co/ufal/robeczech-base, both for PyTorch and TensorFlow.
- 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
29. Self-paced reading experiments on explicit and implicit contrastive and temporal discourse relations in Czech
- Creator:
- Zikánová, Šárka and Smolík, Filip
- Publisher:
- Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)
- Type:
- text, other, and languageDescription
- Subject:
- discourse, psycholinguistic experiments, explicit discourse relations, implicit discourse relations, and self-paced reading
- Language:
- Czech
- Description:
- Supplementary materials for the paper “Processing of explicit and implicit contrastive and temporal discourse relations in Czech” (submitted to Discourse Processes)
- Rights:
- Creative Commons - Attribution 4.0 International (CC BY 4.0), http://creativecommons.org/licenses/by/4.0/, and PUB
30. Sentiment Analysis (Czech Model)
- Creator:
- Vysušilová, Petra and Straka, Milan
- Publisher:
- Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)
- Type:
- text, mlmodel, and languageDescription
- Subject:
- sentiment analysis and BERT
- Language:
- Czech
- Description:
- Sentiment analysis models for Czech language. Models are three Czech sentiment analysis datasets(http://liks.fav.zcu.cz/sentiment/): Mall, CSFD, Facebook, and joint data from all three datasets above, using Czech version of BERT model, RobeCzech. We present the best model for every dataset. Mall and CSFD models are new state-of-the-art for respective data. Demo jupyter notebook is available on the project GitHub. These models are a part of Czech NLP with Contextualized Embeddings master thesis.
- 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
- « Previous
- Next »
- 1
- 2
- 3
- 4