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

Publikation: Beitrag in Buch/Konferenzbericht/Sammelband/GutachtenBeitrag in KonferenzbandBeigetragenBegutachtung

Beitragende

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

OriginalspracheEnglisch
TitelEACL 2023 - 9th Workshop on Slavic Natural Language Processing, Proceedings of the SlavicNLP 2023
Herausgeber (Verlag)The Association for Computational Linguistics
Seiten1-10
Seitenumfang10
ISBN (elektronisch)9781959429579
PublikationsstatusVeröffentlicht - 2023
Peer-Review-StatusJa

Publikationsreihe

ReiheProceedings of the Workshop (SlavicNLP)

Workshop

Titel9th Workshop on Slavic Natural Language Processing
KurztitelSlavic NLP 2023
Veranstaltungsnummer9
Beschreibungheld in conjunction with the 17th Conference of the European Chapter of the Association for Computational Linguistics
Dauer6 Mai 2023
Webseite
OrtValamar Lacroma Dubrovnik & online
StadtDubrovnik
LandKroatien

Externe IDs

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

Schlagworte

ASJC Scopus Sachgebiete