SHAPAQA: Shallow Parsing for Question Answering on the World Wide Web

S. Buchholz, W. Daelemans

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

    58 Downloads (Pure)

    Abstract

    We introduce shapaqa, a shallow parsing approach to online, open-domain question answering on the WorldWideWeb. Given a form-based natural language question as input, the system uses a memory-based shallow parser to analyze web pages retrieved using normal keyword search on a search engine. Two versions of the system are evaluated on a test set of 200 questions. In combination with two back-off methods a mean reciprocal rank of .46 is achieved.
    Original languageEnglish
    Title of host publicationProceedings Euroconference
    Subtitle of host publicationRecent Advances in Natural Language Processing, Tsigov Chark, Bulgaria, 5-7 September 2001
    EditorsG. Angelova, et al.
    Place of PublicationBulgaria
    PublisherTsigov Chark
    Pages47-51
    Number of pages5
    ISBN (Print)9789549090611
    Publication statusPublished - 2001

    Fingerprint Dive into the research topics of 'SHAPAQA: Shallow Parsing for Question Answering on the World Wide Web'. Together they form a unique fingerprint.

  • Cite this

    Buchholz, S., & Daelemans, W. (2001). SHAPAQA: Shallow Parsing for Question Answering on the World Wide Web. In G. Angelova, & et al. (Eds.), Proceedings Euroconference: Recent Advances in Natural Language Processing, Tsigov Chark, Bulgaria, 5-7 September 2001 (pp. 47-51). Tsigov Chark.