UDPipe 2 is a Python prototype, capable of performing tagging, lemmatization and syntactic analysis of CoNLL-U input. It took part in several competitions, reaching excellent results in all of them:

• one of the winners of the CoNLL 2018 Shared Task
• one of the winners of the SIGMORPHON 2019 Shared Task 2
• the winner of EvaLatin 2020

Compared to UDPipe 1, it is Python-only, it does not perform tokenization, and the models require more computation power.

Webservice

The UDPipe 2 models are currently available from the LINDAT UDPipe REST Service. Apart from the web interface, you can use the following Python client script to process your files. TODO

Models

The available models are described on a separate page.

Acknowledgements

This work has been supported by the Ministry of Education, Youth and Sports of the Czech Republic, Project No. LM2018101 LINDAT/CLARIAH-CZ.

Publications

• Milan Straka (2018): UDPipe 2.0 Prototype at CoNLL 2018 UD Shared Task. In: Proceedings of CoNLL 2018: The SIGNLL Conference on Computational Natural Language Learning, pp. 197-207, Association for Computational Linguistics, Stroudsburg, PA, USA, ISBN 978-1-948087-72-8
• Milan Straka, Jana Straková, Jan Hajič (2019): UDPipe at SIGMORPHON 2019: Contextualized Embeddings, Regularization with Morphological Categories, Corpora Merging. In: Proceedings of the 16th SIGMORPHON Workshop on Computational Research in Phonetics, Phonology, and Morphology, pp. 95-103, Association for Computational Linguistics, Stroudsburg, PA, USA, ISBN 978-1-950737-36-9
• Milan Straka, Jana Straková, Jan Hajič (2019): Evaluating Contextualized Embeddings on 54 Languages in POS Tagging, Lemmatization and Dependency Parsing. In: ArXiv.org Computing Research Repository, ISSN 2331-8422, 1904.02099

Bibtex for Referencing

@InProceedings{straka-2018-udpipe,
    title = "{UDP}ipe 2.0 Prototype at {C}o{NLL} 2018 {UD} Shared Task",
    author = "Straka, Milan",
    booktitle = "Proceedings of the {C}o{NLL} 2018 Shared Task: Multilingual Parsing from Raw Text to Universal Dependencies",
    month = oct,
    year = "2018",
    address = "Brussels, Belgium",
    publisher = "Association for Computational Linguistics",
    url = "https://www.aclweb.org/anthology/K18-2020",
    doi = "10.18653/v1/K18-2020",
    pages = "197--207",
}