Query-based extracting: how to support the answer?

W.E. Bosma

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

    39 Downloads (Pure)

    Abstract

    Human-made query-based summaries commonly contain information not explicitly asked for. They answer the user query, but also provide supporting information. In order to find this information in the source text, a graph is used to model the strength and type of relations between sentences of the query and document cluster, based on various features. The resulting extracts rank second in overall readability in the DUC 2006 evaluation. Employment of better question answering methods is the key to improve also content-based evaluation results.
    Original languageUndefined
    Title of host publicationDocument Understanding Conference 2006
    Place of PublicationGaithersburg, MD, USA
    PublisherNational Institute of Standards and Technology
    Pages202-208
    Number of pages7
    ISBN (Print)not assigned
    Publication statusPublished - 8 Jun 2006

    Publication series

    Name
    PublisherNational Institute of Standards and Technology (NIST)
    NumberPaper PMD-

    Keywords

    • EWI-9290
    • METIS-248200
    • IR-66954

    Cite this

    Bosma, W. E. (2006). Query-based extracting: how to support the answer? In Document Understanding Conference 2006 (pp. 202-208). Gaithersburg, MD, USA: National Institute of Standards and Technology.