@inproceedings{saleva-lignos-2024-language,
    title = "Language Model Priors and Data Augmentation Strategies for Low-resource Machine Translation: A Case Study Using {F}innish to {N}orthern {S}{\'a}mi",
    author = {S{\"a}lev{\"a}, Jonne  and
      Lignos, Constantine},
    editor = "Ku, Lun-Wei  and
      Martins, Andre  and
      Srikumar, Vivek",
    booktitle = "Findings of the Association for Computational Linguistics: ACL 2024",
    month = aug,
    year = "2024",
    address = "Bangkok, Thailand",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/fix-sig-urls/2024.findings-acl.768/",
    doi = "10.18653/v1/2024.findings-acl.768",
    pages = "12949--12956",
    abstract = "We investigate ways of using monolingual data in both the source and target languages for improving low-resource machine translation. As a case study, we experiment with translation from Finnish to Northern S{\'a}mi.Our experiments show that while conventional backtranslation remains a strong contender, using synthetic target-side data when training backtranslation models can be helpful as well.We also show that monolingual data can be used to train a language model which can act as a regularizer without any augmentation of parallel data."
}