Predicate-argument reordering based on learning to rank for english-korean machine translation

Joo Young Lee, Gumwon Hong, Hae Chang Rim, Young In Song, Young Sook Hwang

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

    1 Citation (Scopus)

    Abstract

    In this paper, we propose a method of learning predicateargument structure reordering, and present its effect on machine translation. The method takes two steps; first, it extracts generalized predicate-argument structure reordering rules using a source sentence parse tree from a parallel corpus. Second, it trains a model based on learning to rank framework to select the most relevant reordering rule based on source language context features. The learned model is used to restructure a source sentence in order to have similar word order with a target sentence. In our experiments on English-to-Korean machine translation, the proposed method achieves significant improvements in BLEU score, from 19.68 to 21.84.

    Original languageEnglish
    Title of host publicationProceedings of the 5th International Conference on Ubiquitous Information Management and Communication, ICUIMC 2011
    DOIs
    Publication statusPublished - 2011
    Event5th International Conference on Ubiquitous Information Management and Communication, ICUIMC 2011 - Seoul, Korea, Republic of
    Duration: 2011 Feb 212011 Feb 23

    Publication series

    NameProceedings of the 5th International Conference on Ubiquitous Information Management and Communication, ICUIMC 2011

    Other

    Other5th International Conference on Ubiquitous Information Management and Communication, ICUIMC 2011
    Country/TerritoryKorea, Republic of
    CitySeoul
    Period11/2/2111/2/23

    Keywords

    • Learning to rank
    • Machine translation
    • Predicate-argument
    • Preprocessing
    • Reordering

    ASJC Scopus subject areas

    • Computer Networks and Communications
    • Information Systems

    Fingerprint

    Dive into the research topics of 'Predicate-argument reordering based on learning to rank for english-korean machine translation'. Together they form a unique fingerprint.

    Cite this