Dependency relations as source context in phrase-based SMT

R. Haque, S.K. Naskar, A. van den Bosch, A. Way

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

    4 Citations (Scopus)


    The Phrase-Based Statistical Machine Translation (PB-SMT) model has recently begun to include source context modeling, under the assumption that the proper lexical choice of an ambiguous word can be determined from the context in which it appears. Various types of lexical and syntactic features such as words, parts-of-speech, and supertags have been explored as effective source context in SMT. In this paper, we show that position-independent syntactic dependency relations of the head of a source phrase can be modeled as useful source context to improve target phrase selection and thereby improve overall performance of PB-SMT. On a Dutch—English translation task, by combining dependency relations and syntactic contextual features (part-of-speech), we achieved a 1.0 BLEU (Papineni et al., 2002) point improvement (3.1% relative) over the baseline.
    Original languageEnglish
    Title of host publicationPACLIC 23
    Subtitle of host publicationthe 23rd Pacific Asia Conference on Language, Information and Computation
    EditorsB. T'sou, C.-R. Huang
    Place of PublicationHong Kong, China
    Publication statusPublished - 2009


    Dive into the research topics of 'Dependency relations as source context in phrase-based SMT'. Together they form a unique fingerprint.

    Cite this