@inproceedings{lakew-etal-2018-adapting,
    title = "Adapting Multilingual {NMT} to Extremely Low Resource Languages {FBK}`s Participation in the {B}asque-{E}nglish Low-Resource {MT} Task, {IWSLT} 2018",
    author = "Lakew, Surafel M.  and
      Federico, Marcello",
    editor = "Turchi, Marco  and
      Niehues, Jan  and
      Frederico, Marcello",
    booktitle = "Proceedings of the 15th International Conference on Spoken Language Translation",
    month = oct # " 29-30",
    year = "2018",
    address = "Brussels",
    publisher = "International Conference on Spoken Language Translation",
    url = "https://preview.aclanthology.org/add-emnlp-2024-awards/2018.iwslt-1.24/",
    pages = "160--165",
    abstract = "Multilingual neural machine translation (M-NMT) has recently shown to improve performance of machine translation of low-resource languages. Thanks to its implicit transfer-learning mechanism, the availability of a highly resourced language pair can be leveraged to learn useful representation for a lower resourced language. This work investigates how a low-resource translation task can be improved within a multilingual setting. First, we adapt a system trained on multiple language directions to a specific language pair. Then, we utilize the adapted model to apply an iterative training-inference scheme [1] using monolingual data. In the experimental setting, an extremely low-resourced Basque-English language pair (i.e., {\ensuremath{\approx}} 5.6K in-domain training data) is our target translation task, where we considered a closely related French/Spanish-English parallel data to build the multilingual model. Experimental results from an i) in-domain and ii) an out-of-domain setting with additional training data, show improvements with our approach. We report a translation performance of 15.89 with the former and 23.99 BLEU with the latter on the official IWSLT 2018 Basque-English test set."
}