Semantic Scholar Open Access 2023 4 sitasi

Large Language Models for Multilingual Slavic Named Entity Linking

Rinalds Viksna I. Skadina Daiga Deksne Roberts Rozis

Lihat Sumber DOI

Abstrak

This paper describes our submission for the 4th Shared Task on SlavNER on three Slavic languages - Czech, Polish and Russian. We use pre-trained multilingual XLM-R Language Model (Conneau et al., 2020) and fine-tune it for three Slavic languages using datasets provided by organizers. Our multilingual NER model achieves 0.896 F-score on all corpora, with the best result for Czech (0.914) and the worst for Russian (0.880). Our cross-language entity linking module achieves F-score of 0.669 in the official SlavNER 2023 evaluation.

Penulis (4)

Rinalds Viksna

I. Skadina

Daiga Deksne

Roberts Rozis

Format Sitasi

APA MLA BibTeX

Viksna, R., Skadina, I., Deksne, D., Rozis, R. (2023). Large Language Models for Multilingual Slavic Named Entity Linking. https://doi.org/10.18653/v1/2023.bsnlp-1.20

Akses Cepat

Lihat di Sumber doi.org/10.18653/v1/2023.bsnlp-1.20

Informasi Jurnal

Tahun Terbit: 2023
Bahasa: en
Total Sitasi: 4×
Sumber Database: Semantic Scholar
DOI: 10.18653/v1/2023.bsnlp-1.20
Akses: Open Access ✓