@inproceedings{korotkova-fishel-2023-distilling,
    title = "Distilling {E}stonian Text Domains for Production-Oriented Machine Translation",
    author = "Korotkova, Elizaveta  and
      Fishel, Mark",
    editor = {Alum{\"a}e, Tanel  and
      Fishel, Mark},
    booktitle = "Proceedings of the 24th Nordic Conference on Computational Linguistics (NoDaLiDa)",
    month = may,
    year = "2023",
    address = "T{\'o}rshavn, Faroe Islands",
    publisher = "University of Tartu Library",
    url = "https://preview.aclanthology.org/add-emnlp-2024-awards/2023.nodalida-1.78/",
    pages = "772--781",
    abstract = "This paper explores knowledge distillation for multi-domain neural machine translation (NMT). We focus on the Estonian-English translation direction and experiment with distilling the knowledge of multiple domain-specific teacher models into a single student model that is tiny and efficient. Our experiments use a large parallel dataset of 18 million sentence pairs, consisting of 10 corpora, divided into 6 domain groups based on source similarity, and incorporate forward-translated monolingual data. Results show that tiny student models can cope with multiple domains even in case of large corpora, with different approaches benefiting frequent and low-resource domains."
}