English

Larger-Scale Transformers for Multilingual Masked Language Modeling

Computation and Language 2021-05-04 v1

Abstract

Recent work has demonstrated the effectiveness of cross-lingual language model pretraining for cross-lingual understanding. In this study, we present the results of two larger multilingual masked language models, with 3.5B and 10.7B parameters. Our two new models dubbed XLM-R XL and XLM-R XXL outperform XLM-R by 1.8% and 2.4% average accuracy on XNLI. Our model also outperforms the RoBERTa-Large model on several English tasks of the GLUE benchmark by 0.3% on average while handling 99 more languages. This suggests pretrained models with larger capacity may obtain both strong performance on high-resource languages while greatly improving low-resource languages. We make our code and models publicly available.

Keywords

Cite

@article{arxiv.2105.00572,
  title  = {Larger-Scale Transformers for Multilingual Masked Language Modeling},
  author = {Naman Goyal and Jingfei Du and Myle Ott and Giri Anantharaman and Alexis Conneau},
  journal= {arXiv preprint arXiv:2105.00572},
  year   = {2021}
}

Comments

4 pages

R2 v1 2026-06-24T01:42:59.113Z