@inproceedings{vincent-etal-2022-controlling,
    title = "Controlling Formality in Low-Resource {NMT} with Domain Adaptation and Re-Ranking: {SLT}-{CDT}-{U}o{S} at {IWSLT}2022",
    author = {Vincent, Sebastian  and
      Barrault, Lo{\"i}c  and
      Scarton, Carolina},
    editor = "Salesky, Elizabeth  and
      Federico, Marcello  and
      Costa-juss{\`a}, Marta",
    booktitle = "Proceedings of the 19th International Conference on Spoken Language Translation (IWSLT 2022)",
    month = may,
    year = "2022",
    address = "Dublin, Ireland (in-person and online)",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/fix-sig-urls/2022.iwslt-1.31/",
    doi = "10.18653/v1/2022.iwslt-1.31",
    pages = "341--350",
    abstract = "This paper describes the SLT-CDT-UoS group{'}s submission to the first Special Task on Formality Control for Spoken Language Translation, part of the IWSLT 2022 Evaluation Campaign. Our efforts were split between two fronts: data engineering and altering the objective function for best hypothesis selection. We used language-independent methods to extract formal and informal sentence pairs from the provided corpora; using English as a pivot language, we propagated formality annotations to languages treated as zero-shot in the task; we also further improved formality controlling with a hypothesis re-ranking approach. On the test sets for English-to-German and English-to-Spanish, we achieved an average accuracy of .935 within the constrained setting and .995 within unconstrained setting. In a zero-shot setting for English-to-Russian and English-to-Italian, we scored average accuracy of .590 for constrained setting and .659 for unconstrained."
}