Paraphrase Substitution for Recognizing Textual Entailment

W.E. Bosma, C. Callison-Burch

    Research output: Chapter in Book/Report/Conference proceedingChapterAcademicpeer-review

    4 Citations (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 find 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 publicationEvaluation of Multilingual and Multi-modal Information Retrieval
    EditorsC. Peters, P. Clough, F.C. Gey, J. Karlgren, B. Magnini, D.W. Oard, M. de Rijke, M. Stempfhuber
    Place of PublicationBerlin
    PublisherSpringer
    Pages502-509
    Number of pages8
    ISBN (Print)978-3-540-74998-1
    DOIs
    Publication statusPublished - 2007

    Publication series

    NameLecture Notes in Computer Science
    PublisherSpringer Verlag
    NumberPaper P-NS/4730
    Volume4730
    ISSN (Print)0302-9743
    ISSN (Electronic)1611-3349

    Keywords

    • HMI-SLT: Speech and Language Technology
    • METIS-245759
    • IR-64445
    • EWI-11353

    Cite this