%0 Conference Paper %1 d5ae2c3f3d6741fd931a4dea1d50ebe8 %A Torge, Sunna %A Politov, Andrei %A Lehmann, Christoph %A Saffar, Bochra %A Tao, Ziyan %B EACL 2023 - 9th Workshop on Slavic Natural Language Processing, Proceedings of the SlavicNLP 2023 %D 2023 %I The Association for Computational Linguistics %K area_architectures unit_transfer FIS_scads imported %P 1--10 %T Named Entity Recognition for Low-Resource Languages - Profiting from Language Families %U https://bsnlp.cs.helsinki.fi/ %X Machine learning drives forward the development in many areas of Natural Language Processing (NLP). Until now, many NLP systems and research are focusing on high-resource languages, i.e. languages for which many data resources exist. Recently, so-called low-resource languages increasingly come into focus. In this context, multi-lingual language models, which are trained on related languages to a target low-resource language, may enable NLP tasks on this low-resource language. In this work, we investigate the use of multi-lingual models for Named Entity Recognition (NER) for low-resource languages. We consider the West Slavic language family and the low-resource languages Upper Sorbian and Kashubian. Three RoBERTa models were trained from scratch, two mono-lingual models for Czech and Polish, and one bi-lingual model for Czech and Polish. These models were evaluated on the NER downstream task for Czech, Polish, Upper Sorbian, and Kashubian, and compared to existing state-of-the-art models such as RobeCzech, HerBERT, and XLM-R. The results indicate that the mono-lingual models perform better on the language they were trained on, and both the mono-lingual and language family models outperform the large multi-lingual model in downstream tasks. Overall, the study shows that low-resource West Slavic languages can benefit from closely related languages and their models.

@inproceedings{d5ae2c3f3d6741fd931a4dea1d50ebe8, abstract = {Machine learning drives forward the development in many areas of Natural Language Processing (NLP). Until now, many NLP systems and research are focusing on high-resource languages, i.e. languages for which many data resources exist. Recently, so-called low-resource languages increasingly come into focus. In this context, multi-lingual language models, which are trained on related languages to a target low-resource language, may enable NLP tasks on this low-resource language. In this work, we investigate the use of multi-lingual models for Named Entity Recognition (NER) for low-resource languages. We consider the West Slavic language family and the low-resource languages Upper Sorbian and Kashubian. Three RoBERTa models were trained from scratch, two mono-lingual models for Czech and Polish, and one bi-lingual model for Czech and Polish. These models were evaluated on the NER downstream task for Czech, Polish, Upper Sorbian, and Kashubian, and compared to existing state-of-the-art models such as RobeCzech, HerBERT, and XLM-R. The results indicate that the mono-lingual models perform better on the language they were trained on, and both the mono-lingual and language family models outperform the large multi-lingual model in downstream tasks. Overall, the study shows that low-resource West Slavic languages can benefit from closely related languages and their models.}, added-at = {2024-11-28T16:27:18.000+0100}, author = {Torge, Sunna and Politov, Andrei and Lehmann, Christoph and Saffar, Bochra and Tao, Ziyan}, biburl = {https://puma.scadsai.uni-leipzig.de/bibtex/25dd9604d3e05e770b3466e6878813b82/scadsfct}, booktitle = {EACL 2023 - 9th Workshop on Slavic Natural Language Processing, Proceedings of the SlavicNLP 2023}, interhash = {c211c9eaad7cf00ad19df5901b391e11}, intrahash = {5dd9604d3e05e770b3466e6878813b82}, keywords = {area_architectures unit_transfer FIS_scads imported}, language = {English}, note = {Publisher Copyright: {\textcopyright} 2023 Association for Computational Linguistics.; 9th Workshop on Slavic Natural Language Processing, Slavic NLP 2023 ; Conference date: 06-05-2023 Through 06-05-2023}, pages = {1--10}, publisher = {The Association for Computational Linguistics}, series = {Proceedings of the Workshop (SlavicNLP)}, timestamp = {2024-12-06T14:36:51.000+0100}, title = {Named Entity Recognition for Low-Resource Languages - Profiting from Language Families}, url = {https://bsnlp.cs.helsinki.fi/}, year = 2023 }