@inproceedings{khusainova-etal-2021-hierarchical,
    title = "Hierarchical Transformer for Multilingual Machine Translation",
    author = "Khusainova, Albina  and
      Khan, Adil  and
      Rivera, Ad{\'\i}n Ram{\'\i}rez  and
      Romanov, Vitaly",
    editor = {Zampieri, Marcos  and
      Nakov, Preslav  and
      Ljube{\v{s}}i{\'c}, Nikola  and
      Tiedemann, J{\"o}rg  and
      Scherrer, Yves  and
      Jauhiainen, Tommi},
    booktitle = "Proceedings of the Eighth Workshop on NLP for Similar Languages, Varieties and Dialects",
    month = apr,
    year = "2021",
    address = "Kiyv, Ukraine",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2021.vardial-1.2",
    pages = "12--20",
    abstract = "The choice of parameter sharing strategy in multilingual machine translation models determines how optimally parameter space is used and hence, directly influences ultimate translation quality. Inspired by linguistic trees that show the degree of relatedness between different languages, the new general approach to parameter sharing in multilingual machine translation was suggested recently. The main idea is to use these expert language hierarchies as a basis for multilingual architecture: the closer two languages are, the more parameters they share. In this work, we test this idea using the Transformer architecture and show that despite the success in previous work there are problems inherent to training such hierarchical models. We demonstrate that in case of carefully chosen training strategy the hierarchical architecture can outperform bilingual models and multilingual models with full parameter sharing.",
}