Normalized Alignment of Dependency Trees for Detecting Textual Entailment

E. Marsi, E. Krahmer, W.E. Bosma, Mariet Theune

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

    33 Downloads (Pure)

    Abstract

    In this paper, we investigate the usefulness of normalized alignment of dependency trees for entailment prediction. Overall, our approach yields an accuracy of 60% on the RTE2 test set, which is a significant improvement over the baseline. Results vary substantially across the different subsets, with a peak performance on the summarization data. We conclude that normalized alignment is useful for detecting textual entailments, but a robust approach will probably need to include additional sources of information.
    Original languageUndefined
    Title of host publicationSecond PASCAL Recognising Textual Entailment Challenge
    EditorsB. Magnini, I. Dagan
    PublisherSpringer
    Pages56-61
    Number of pages6
    ISBN (Print)not assigned
    Publication statusPublished - Apr 2006
    EventSecond PASCAL Recognising Textual Entailment Challenge, Venice, Italy: Second PASCAL Recognising Textual Entailment Challenge -
    Duration: 1 Apr 2006 → …

    Publication series

    Name
    Number2

    Conference

    ConferenceSecond PASCAL Recognising Textual Entailment Challenge, Venice, Italy
    Period1/04/06 → …

    Keywords

    • METIS-238159
    • EWI-6882
    • IR-66341

    Cite this