This is a trained model for the supervised machine learning tool NameTag 3 (https://ufal.mff.cuni.cz/nametag/3/), trained on the Czech Named Entity Corpus 2.0 (https://ufal.mff.cuni.cz/cnec/cnec2.0). NameTag 3 is an open-source tool for both flat and nested named entity recognition (NER). NameTag 3 identifies proper names in text and classifies them into a set of predefined categories, such as names of persons, locations, organizations, etc. The model documentation can be found at https://ufal.mff.cuni.cz/nametag/3/models#czech-cnec2.
This is a trained model for the supervised machine learning tool NameTag 3 (https://ufal.mff.cuni.cz/nametag/3/), trained jointly on several NE corpora: English CoNLL-2003, German CoNLL-2003, Dutch CoNLL-2002, Spanish CoNLL-2002, Ukrainian Lang-uk, and Czech CNEC 2.0, all harmonized to flat NEs with 4 labels PER, ORG, LOC, and MISC. NameTag 3 is an open-source tool for both flat and nested named entity recognition (NER). NameTag 3 identifies proper names in text and classifies them into a set of predefined categories, such as names of persons, locations, organizations, etc. The model documentation can be found at https://ufal.mff.cuni.cz/nametag/3/models#multilingual-conll.
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.
In the last ten years, the Czech Republic participated in numerous international comparative studies measuring knowledge and skills of school children in various subject areas. The studies have brought a lot of notable information on gender differences in student outcomes. Unfortunately, these findings met very limited attention of the Czech society and educational policymakers. The aim of this article is to summarize key findings about gender differences in the areas of reading, mathematics and science and to show the relationships between student results and their educational aspirations and attitudes.
The aim of this paper is to explore the impact of the structure of the Czech education system on the development of the relationship between a student's achievement and his/her family background. It compares the strength of the relationship between student achievement and a student's family background in various stages of his/her education career (grades 4, 8 and 10) in the Czech Republic and in systems without early tracking that also exhibit high student performance (Canada, Nordic countries). In addition, the paper tests a hypothesis that systems with different levels of tracking differ not only in their structure but also in teaching methods and teachers' attitudes. The analysis was conducted on data sets from the IEA PIRLS 2001, the IEA TIMSS 1999, and the OECD PISA 2003.
The latinpipe-evalatin24-240520 is a PhilBerta-based model for LatinPipe 2024 <https://github.com/ufal/evalatin2024-latinpipe>, performing tagging, lemmatization, and dependency parsing of Latin, based on the winning entry to the EvaLatin 2024 <https://circse.github.io/LT4HALA/2024/EvaLatin> shared task. It is released under the CC BY-NC-SA 4.0 license.
UDPipe is an trainable pipeline for tokenization, tagging, lemmatization and dependency parsing of CoNLL-U files. UDPipe is language-agnostic and can be trained given only annotated data in CoNLL-U format. Trained models are provided for nearly all UD treebanks. UDPipe is available as a binary, as a library for C++, Python, Perl, Java, C#, and as a web service.
UDPipe is a free software under Mozilla Public License 2.0 (http://www.mozilla.org/MPL/2.0/) and the linguistic models are free for non-commercial use and distributed under CC BY-NC-SA (http://creativecommons.org/licenses/by-nc-sa/4.0/) license, although for some models the original data used to create the model may impose additional licensing conditions. UDPipe is versioned using Semantic Versioning (http://semver.org/).
UDPipe website http://ufal.mff.cuni.cz/udpipe contains download links of both the released packages and trained models, hosts documentation and offers online demo.
UDPipe development repository http://github.com/ufal/udpipe is hosted on GitHub.
UDPipe 2 is a POS tagger, lemmatizer and dependency parser.
Compared to UDPipe 1:
- UDPipe 2 is Python-only and tested only in Linux,
- UDPipe 2 is meant as a research tool, not as a user-friendly UDPipe 1 replacement,
- UDPipe 2 achieves much better performance, but requires a GPU for reasonable performance,
- UDPipe 2 does not perform tokenization by itself – it uses UDPipe 1 for that.
UDPipe 2 is available in the udpipe-2 branch of the UDPipe repository at https://github.com/ufal/udpipe/tree/udpipe-2. It is a free software under Mozilla Public License 2.0 (http://www.mozilla.org/MPL/2.0/) and the models are free for non-commercial use and distributed under CC BY-NC-SA (http://creativecommons.org/licenses/by-nc-sa/4.0/) license, although for some models the original data used to create the model may impose additional licensing conditions.
UDPipe 2 is also available as a REST service running at https://lindat.mff.cuni.cz/services/udpipe. If you like, you can use the https://github.com/ufal/udpipe/blob/udpipe-2/udpipe2_client.py script to interact with it.