Supertags as source language context in hierarchical phrase-based SMT

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

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

    10 Citations (Scopus)


    Statistical machine translation (SMT) models have recently begun to include source context modeling, under the assumption that the proper lexical choice of the translation for an ambiguous word can be determined from the
    context in which it appears. Various types of lexical and syntactic features have been explored as effective source context to improve phrase selection in SMT. In the present work, we introduce lexico-syntactic descriptions in the form of supertags as source-side context features in the state-of-the-art hierarchical phrase-based SMT (HPB) model. These features enable us to exploit source similarity in addition to target similarity, as modelled by the language model. In our experiments two kinds of supertags are employed: those from lexicalized tree-adjoining grammar (LTAG) and combinatory categorial grammar (CCG). We use a memory-based classification framework that enables the efficient estimation of these features. Despite the differences between the two supertagging approaches, they give similar improvements. We evaluate the performance of our approach on an English-to-Dutch translation task, and report statistically significant improvements of 4.48% and 6.3% BLEU scores in translation quality when adding CCG and LTAG supertags, respectively, as context-informed features.
    Original languageEnglish
    Title of host publicationProceedings of AMTA 2010
    Subtitle of host publicationThe Ninth Conference of the Association for Machine Translation in the Americas
    Place of PublicationDenver, Colorado
    Publication statusPublished - 2010


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

    Cite this