@inproceedings{wu-etal-2024-far,
    title = "How Far can 100 Samples Go? Unlocking Zero-Shot Translation with Tiny Multi-Parallel Data",
    author = "Wu, Di  and
      Tan, Shaomu  and
      Meng, Yan  and
      Stap, David  and
      Monz, Christof",
    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/add-emnlp-2024-awards/2024.findings-acl.896/",
    doi = "10.18653/v1/2024.findings-acl.896",
    pages = "15092--15108",
    abstract = "Zero-shot translation aims to translate between language pairs not seen during training in Multilingual Machine Translation (MMT) and is widely considered an open problem. A common, albeit resource-consuming, solution is to add as many related translation directions as possible to the training corpus. In this paper, we show that for an English-centric model, surprisingly large zero-shot improvements can be achieved by simply fine-tuning with a very small amount of multi-parallel data. For example, on the EC30 dataset, we obtain up to +21.7 ChrF++ non-English overall improvements (870 directions) by using only 100 multi-parallel samples while preserving English-centric translation quality. This performance exceeds M2M100 by an average of 5.9 ChrF++ in the involved non-English directions. When investigating the size effect of fine-tuning data on translation quality, we found that already a small, randomly sampled set of fine-tuning directions is sufficient to achieve comparable improvements. The resulting non-English performance is close to the complete translation upper bound. Even in a minimal setting{---}fine-tuning with only one single sample{---}the well-known off-target issue is almost completely resolved, explaining parts{---}but not all{---}of the observed improvements in translation quality."
}