Paraphrase substitution for recognizing textual entailment

W.E. Bosma, C. Callison-Burch

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

    1 Citation (Scopus)

    Abstract

    We describe a method for recognizing textual entailment that uses the length of the longest common subsequence (LCS) between two texts as its decision criterion. Rather than requiring strict word matching in the common subsequences, we perform a flexible match using automatically generated paraphrases. We ��?nd that the use of paraphrases over strict word matches represents an average F-measure improvement from 0.22 to 0.36 on the CLEF 2006 Answer Validation Exercise for 7 languages.
    Original languageUndefined
    Title of host publicationWorking Notes of CLEF 2006
    EditorsA. Nardi, C. Peters, J.L. Vicedo
    PublisherCLEF
    Pages1-8
    Number of pages8
    ISBN (Print)2-912335-23-x
    Publication statusPublished - 20 Sep 2006
    Event7th Workshop of the Cross-Language Evaluation Forum, CLEF 2006 - Alicante, Spain
    Duration: 20 Sep 200622 Sep 2006
    Conference number: 7

    Publication series

    Name
    PublisherCLEF
    Number10
    ISSN (Print)1818-8044

    Workshop

    Workshop7th Workshop of the Cross-Language Evaluation Forum, CLEF 2006
    Abbreviated titleCLEF 2006
    CountrySpain
    CityAlicante
    Period20/09/0622/09/06

    Keywords

    • EWI-9709
    • IR-64000
    • METIS-248215
    • HMI-SLT: Speech and Language Technology

    Cite this