Word Transition Entropy as an Indicator for Expected Machine Translation Quality

Michael Carl, Moritz Schaeffer

    Publikation: Bidrag til bog/antologi/rapportKonferencebidrag i proceedingsForskningpeer review

    Abstrakt

    While most machine translation evaluation techniques (BLEU, NIST, TER, METEOR) assess translation quality based on a set of reference translations, we suggest to evaluate the literality of a set of (human or machine generated) translations to infer their potential quality. We provide evidence which suggests that more literal translations are produced more easily, by humans and machine, and are also less error prone. Literal translations may not be appropriate or even possible for all languages, types of texts, and translation purposes. However, in this paper we show that an assessment of the literality of translations allows us to (1) evaluate human and machine translations in a similar fashion and (2) may be instrumental to predict machine translation quality scores,
    OriginalsprogEngelsk
    TitelProceedings of the Workshop on Automatic and Manual Metrics for Operational Translation Evaluation. MTE 2014
    RedaktørerKeith J. Miller, Lucia Specia, Kim Harris, Stacey Bailey
    UdgivelsesstedParis
    ForlagEuropean Language Resources Association
    Publikationsdato2014
    Sider45-50
    StatusUdgivet - 2014
    BegivenhedThe Workshop on Automatic and Manual Metrics for Operational Translation Evaluation. MTE 2014 - Harpa Conference Centre , Reykjavik, Island
    Varighed: 26 maj 201426 maj 2014
    http://mte2014.github.io/

    Workshop

    WorkshopThe Workshop on Automatic and Manual Metrics for Operational Translation Evaluation. MTE 2014
    LokationHarpa Conference Centre
    Land/OmrådeIsland
    ByReykjavik
    Periode26/05/201426/05/2014
    AndetHeld in connection to the LREC 2014: The 9th edition of the Language Resources and Evaluation Conference
    Internetadresse

    Bibliografisk note

    Workshop on The Ninth International Conferencen on Language Resources and Evaluation. LREC 2014

    Emneord

    • Word translation entropy,
    • Edit distance
    • Literality threshold

    Citationsformater