As Little as Possible, as Much as Necessary: Detecting Over- and Undertranslations with Contrastive Conditioning

Jannis Vamvas; Rico Sennrich

ACL 2022short24 citations

As Little as Possible, as Much as Necessary: Detecting Over- and Undertranslations with Contrastive Conditioning

Abstract

Omission and addition of content is a typical issue in neural machine translation. We propose a method for detecting such phenomena with off-the-shelf translation models. Using contrastive conditioning, we compare the likelihood of a full sequence under a translation model to the likelihood of its parts, given the corresponding source or target sequence. This allows to pinpoint superfluous words in the translation and untranslated words in the source even in the absence of a reference translation. The accuracy of our method is comparable to a supervised method that requires a custom quality estimation model.

BibTeX

@inproceedings{vamvas-sennrich-2022-little,
    title = "As Little as Possible, as Much as Necessary: Detecting Over- and Undertranslations with Contrastive Conditioning",
    author = "Vamvas, Jannis  and
      Sennrich, Rico",
    editor = "Muresan, Smaranda  and
      Nakov, Preslav  and
      Villavicencio, Aline",
    booktitle = "Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)",
    month = may,
    year = "2022",
    address = "Dublin, Ireland",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2022.acl-short.53/",
    doi = "10.18653/v1/2022.acl-short.53",
    pages = "490--500"
}