Home  | Publications | ILK+23

Glot500: Scaling Multilingual Corpora and Language Models to 500 Languages

MCML Authors

Link to Profile Hinrich Schütze PI Matchmaking

Hinrich Schütze

Prof. Dr.

Principal Investigator

Computational Linguistics

Abstract

The NLP community has mainly focused on scaling Large Language Models (LLMs) vertically, i.e., making them better for about 100 languages. We instead scale LLMs horizontally: we create, through continued pretraining, Glot500-m, an LLM that covers 511 predominantly low-resource languages. An important part of this effort is to collect and clean Glot500-c, a corpus that covers these 511 languages and allows us to train Glot500-m. We evaluate Glot500-m on five diverse tasks across these languages. We observe large improvements for both high-resource and low-resource languages compared to an XLM-R baseline. Our analysis shows that no single factor explains the quality of multilingual LLM representations. Rather, a combination of factors determines quality including corpus size, script, 'help' from related languages and the total capacity of the model. Our work addresses an important goal of NLP research: we should notlimit NLP to a small fraction of the world’s languages and instead strive to support as many languages as possible to bring the benefits of NLP technology to all languages and cultures.

inproceedings

ACL 2023

61th Annual Meeting of the Association for Computational Linguistics. Toronto, Canada, Jul 09-14, 2023.
Conference logo
A* Conference

Authors

A. Imani • P. Lin • A. H. Kargaran • S. Severini • M. J. Sabet • N. Kassner • C. Ma • H. Schmid • A. Martins • F. Yvon • H. Schütze

Links

DOI GitHub

Research Area

 B2 | Natural Language Processing

BibTeXKey: ILK+23

Back to Top