@inproceedings{sang-etal-2025-federated,
    title = "Federated Meta-Learning for Low-Resource Translation of {K}irundi",
    author = "Sang, Kyle Rui  and
      Rabbani, Tahseen  and
      Zhou, Tianyi",
    editor = "Holdt, {\v{S}}pela Arhar  and
      Ilinykh, Nikolai  and
      Scalvini, Barbara  and
      Bruton, Micaella  and
      Debess, Iben Nyholm  and
      Tudor, Crina Madalina",
    booktitle = "Proceedings of the Third Workshop on Resources and Representations for Under-Resourced Languages and Domains (RESOURCEFUL-2025)",
    month = mar,
    year = "2025",
    address = "Tallinn, Estonia",
    publisher = "University of Tartu Library, Estonia",
    url = "https://preview.aclanthology.org/fix-sig-urls/2025.resourceful-1.34/",
    pages = "190--194",
    ISBN = "978-9908-53-121-2",
    abstract = "In this work, we reframe multilingual neural machine translation (NMT) as a federated meta-learning problem and introduce a translation dataset for the low-resource Kirundi language. We aggregate machine translation models () locally trained on varying (but related) source languages to produce a global meta-model that encodes abstract representations of key semantic structures relevant to the parent languages. We then use the Reptile algorithm and Optuna fine-tuning to fit the global model onto a target language. The target language may live outside the subset of parent languages (such as closely-related dialects or sibling languages), which is particularly useful for languages with limitedly available sentence pairs. We first develop a novel dataset of Kirundi-English sentence pairs curated from Biblical translation. We then demonstrate that a federated learning approach can produce a tiny 4.8M Kirundi translation model and a stronger NLLB-600M model which performs well on both our Biblical corpus and the FLORES-200 Kirundi corpus."
}