Glot500: Scaling Multilingual Corpora and Language Models to 500 Languages - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2023

Glot500: Scaling Multilingual Corpora and Language Models to 500 Languages

Résumé

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 not limit 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. Code, data and models are available at https://github.com/cisnlp/Glot500.
Fichier principal
Vignette du fichier
2023.acl-long.61.pdf (610.29 Ko) Télécharger le fichier
Origine Fichiers éditeurs autorisés sur une archive ouverte

Dates et versions

hal-04163023 , version 1 (17-07-2023)

Licence

Identifiants

  • HAL Id : hal-04163023 , version 1

Citer

Ayyoob Imani, Peiqin Lin, Amir Hossein Kargaran, Silvia Severini, Masoud Jalili Sabet, et al.. Glot500: Scaling Multilingual Corpora and Language Models to 500 Languages. 61th Annual Meeting of the Association for Computational Linguistics, ACL, Jul 2023, Toronto, Canada. ⟨hal-04163023⟩
32 Consultations
82 Téléchargements

Partager

Gmail Mastodon Facebook X LinkedIn More