Modelling Human Translator Behaviour with User-Activity Data

Michael Carl, Arnt Lykke Jakobsen, Kristian Tangsgaard Hvelplund Jensen

    Research output: Chapter in Book/Report/Conference proceedingArticle in proceedingsResearchpeer-review

    9 Downloads (Pure)


    Nagao [8] suggests to model machine translation as an imitation of a
    process that can be observed in human translation behavior. However, not much
    work has been done in anMT context that looks intohuman translationprocesses.
    This paper seeks to introduce a research method for the investigation of human
    translation behavior based on User-Activity Data (UAD) which consists of the
    translator’s recorded keystroke and eye-movement behavior and which can be re-
    played and analysed off-line. The paper gives the background of this technique
    and an example on a English-to-Danish translation. Our goal is to elaborate and
    investigate cognitively grounded basic translation concepts which are material-
    ized and traceable in the UAD.
    Original languageEnglish
    Title of host publicationProceedings of  the Twelfth EAMT Conference 22-­23 September 2008
    EditorsJohn Hutchins, Walther v. Hahn
    Number of pages6
    Place of PublicationHamburg
    PublisherHITEC e.V
    Publication date2008
    ISBN (Print)9783000257704
    Publication statusPublished - 2008
    EventThe 12th Annual Conference of the European Association for Machine Translation. EAMT 2008 - University of Hamburg, Hamburg, Germany
    Duration: 22 Sep 200823 Sep 2008
    Conference number: 12


    ConferenceThe 12th Annual Conference of the European Association for Machine Translation. EAMT 2008
    LocationUniversity of Hamburg
    Internet address


    • Eye trackning
    • User-Activity Data

    Cite this