Named Entity Recognition for Low-Resource Languages - Profiting from Language Families

Research output: Contribution to book/conference proceedings/anthology/reportConference contributionContributedpeer-review

Contributors

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.

Details

Original languageEnglish
Title of host publicationEACL 2023 - 9th Workshop on Slavic Natural Language Processing, Proceedings of the SlavicNLP 2023
PublisherThe Association for Computational Linguistics
Pages1-10
Number of pages10
ISBN (electronic)9781959429579
Publication statusPublished - 2023
Peer-reviewedYes

Publication series

SeriesProceedings of the Workshop (SlavicNLP)

Workshop

Title9th Workshop on Slavic Natural Language Processing
Abbreviated titleSlavic NLP 2023
Conference number9
Descriptionheld in conjunction with the 17th Conference of the European Chapter of the Association for Computational Linguistics
Duration6 May 2023
Website
LocationValamar Lacroma Dubrovnik & online
CityDubrovnik
CountryCroatia

External IDs

ORCID /0000-0001-9756-6390/work/146644781
ORCID /0000-0003-2684-102X/work/146646156

Keywords

ASJC Scopus subject areas