arXiv Open Access 2022

Adapting BigScience Multilingual Model to Unseen Languages

Zheng-Xin Yong Vassilina Nikoulina

Lihat Sumber

Abstrak

We benchmark different strategies of adding new languages (German and Korean) into the BigScience's pretrained multilingual language model with 1.3 billion parameters that currently supports 13 languages. We investigate the factors that affect the language adaptability of the model and the trade-offs between computational costs and expected performance.

Topik & Kata Kunci

cs.CL cs.AI cs.LG

Penulis (2)

Zheng-Xin Yong

Vassilina Nikoulina

Format Sitasi

APA MLA BibTeX

Yong, Z., Nikoulina, V. (2022). Adapting BigScience Multilingual Model to Unseen Languages. https://arxiv.org/abs/2204.04873

Akses Cepat

Lihat di Sumber

Informasi Jurnal

Tahun Terbit: 2022
Bahasa: en
Sumber Database: arXiv
Akses: Open Access ✓