@inproceedings{downey-etal-2024-targeted,
    title = "Targeted Multilingual Adaptation for Low-resource Language Families",
    author = "Downey, C. M.  and
      Blevins, Terra  and
      Serai, Dhwani  and
      Parikh, Dwija  and
      Steinert-Threlkeld, Shane",
    editor = "Al-Onaizan, Yaser  and
      Bansal, Mohit  and
      Chen, Yun-Nung",
    booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2024",
    month = nov,
    year = "2024",
    address = "Miami, Florida, USA",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/fix-sig-urls/2024.findings-emnlp.918/",
    doi = "10.18653/v1/2024.findings-emnlp.918",
    pages = "15647--15663",
    abstract = "Massively multilingual models are known to have limited utility in any one language, and to perform particularly poorly on low-resource languages. By contrast, targeted multinguality has been shown to benefit low-resource languages. To test this approach more rigorously, we systematically study best practices for adapting a pre-trained model to a language family. Focusing on the Uralic family as a test case, we adapt XLM-R under various configurations to model 15 languages; we then evaluate the performance of each experimental setting on two downstream tasks and 11 evaluation languages. Our adapted models significantly outperform mono- and multilingual baselines. A regression analysis reveals that adapted vocabulary size is relatively unimportant for low-resource languages, and that low-resource languages can be aggressively up-sampled during training at little detriment to performance in high-resource languages. These results introduce new best practices for performing language adaptation in a targeted setting."
}