Reassessing Claims of Human Parity and Super-Human Performance in Machine Translation at WMT 2019

Antonio Toral*

*Corresponding author for this work

    Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

    10 Downloads (Pure)

    Abstract

    We reassess the claims of human parity and super-human performance made at the news shared task of WMT2019 for three translation directions: English > German, English > Russian and German >English. First we identify three potential issues in the human evaluation of that shared task: (i) the limited amount of intersentential context available, (ii) the limited translation proficiency of the evaluators and (iii) the use of a reference translation. We then conduct a modified evaluation taking these issues into account. Our results indicate that all the claims of human parity and super-human performance made at WMT2019 should be refuted, except the claim of human parity for English > German. Based on our findings, we put forward a set of recommendations and open questions for future assessments of human parity in machine translation.
    Original languageEnglish
    Title of host publicationProceedings of the 22nd Annual Conference of the European Association for Machine Translation
    Place of PublicationLisboa, Portugal
    PublisherEuropean Association for Machine Translation
    Pages185-194
    Number of pages10
    Publication statusPublished - 2020
    EventAnnual Conference of the European Association for Machine Translation - Online, Portugal
    Duration: 3-Nov-20205-Nov-2020
    Conference number: 22

    Conference

    ConferenceAnnual Conference of the European Association for Machine Translation
    Country/TerritoryPortugal
    Period03/11/202005/11/2020

    Cite this