The Effect of Translationese in Machine Translation Test Sets

Mike Zhang, Antonio Toral

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

    181 Downloads (Pure)

    Abstract

    The effect of translationese has been studied in the field of machine translation (MT), mostly with respect to training data. We study in depth the effect of translationese on test data, using the test sets from the last three editions of WMT’s news shared task, containing 17 translation directions. We show evidence that (i) the use of translationese in test sets results in inflated human evaluation scores for MT systems; (ii) in some cases system rankings do change and (iii) the impact translationese has on a translation direction is inversely correlated to the translation quality attainable by state-of-the-art MT systems for that direction.
    Original languageEnglish
    Title of host publicationProceedings of the Fourth Conference on Machine Translation
    PublisherAssociation for Computational Linguistics (ACL)
    Pages73-81
    Number of pages9
    Volume1
    Publication statusPublished - Aug-2019

    Fingerprint

    Dive into the research topics of 'The Effect of Translationese in Machine Translation Test Sets'. Together they form a unique fingerprint.

    Cite this