@inproceedings{dale-2022-first,
    title = "The first neural machine translation system for the {E}rzya language",
    author = "Dale, David",
    editor = "Serikov, Oleg  and
      Voloshina, Ekaterina  and
      Postnikova, Anna  and
      Klyachko, Elena  and
      Neminova, Ekaterina  and
      Vylomova, Ekaterina  and
      Shavrina, Tatiana  and
      Ferrand, Eric Le  and
      Malykh, Valentin  and
      Tyers, Francis  and
      Arkhangelskiy, Timofey  and
      Mikhailov, Vladislav  and
      Fenogenova, Alena",
    booktitle = "Proceedings of the first workshop on NLP applications to field linguistics",
    month = oct,
    year = "2022",
    address = "Gyeongju, Republic of Korea",
    publisher = "International Conference on Computational Linguistics",
    url = "https://preview.aclanthology.org/add-emnlp-2024-awards/2022.fieldmatters-1.6/",
    pages = "45--53",
    abstract = "We present the first neural machine translation system for translation between the endangered Erzya language and Russian and the dataset collected by us to train and evaluate it. The BLEU scores are 17 and 19 for translation to Erzya and Russian respectively, and more than half of the translations are rated as acceptable by native speakers. We also adapt our model to translate between Erzya and 10 other languages, but without additional parallel data, the quality on these directions remains low. We release the translation models along with the collected text corpus, a new language identification model, and a multilingual sentence encoder adapted for the Erzya language. These resources will be available at \url{https://github.com/slone-nlp/myv-nmt}."
}