Semantic Scholar Open Access 2023 2 sitasi

Analysis of Transfer Learning for Named Entity Recognition in South-Slavic Languages

Nikola Ivačič Thi-Hanh Tran Boshko Koloski S. Pollak Matthew Purver

Lihat Sumber DOI

Abstrak

This paper analyzes a Named Entity Recognition task for South-Slavic languages using the pre-trained multilingual neural network models. We investigate whether the performance of the models for a target language can be improved by using data from closely related languages. We have shown that the model performance is not influenced substantially when trained with other than a target language. While for Slovene, the monolingual setting generally performs better, for Croatian and Serbian the results are slightly better in selected cross-lingual settings, but the improvements are not large. The most significant performance improvement is shown for the Serbian language, which has the smallest corpora. Therefore, fine-tuning with other closely related languages may benefit only the “low resource” languages.

Penulis (5)

Nikola Ivačič

Thi-Hanh Tran

Boshko Koloski

S. Pollak

Matthew Purver

Format Sitasi

APA MLA BibTeX

Ivačič, N., Tran, T., Koloski, B., Pollak, S., Purver, M. (2023). Analysis of Transfer Learning for Named Entity Recognition in South-Slavic Languages. https://doi.org/10.18653/v1/2023.bsnlp-1.13

Akses Cepat

Lihat di Sumber doi.org/10.18653/v1/2023.bsnlp-1.13

Informasi Jurnal

Tahun Terbit: 2023
Bahasa: en
Total Sitasi: 2×
Sumber Database: Semantic Scholar
DOI: 10.18653/v1/2023.bsnlp-1.13
Akses: Open Access ✓