Context based wikipedia linking

Michael Granitzer, Christin Seifert, Mario Zechner

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

    2 Citations (Scopus)

    Abstract

    Automatically linking Wikipedia pages can be done either content based by exploiting word similarities or structure based by exploiting characteristics of the link graph. Our approach focuses on a content based strategy by detecting Wikipedia titles as link candidates and selecting the most relevant ones as links. The relevance calculation is based on the context, i.e. the surrounding text of a link candidate. Our goal was to evaluate the influence of the link-context on selecting relevant links and determining a links best-entry-point. Results show, that a whole Wikipedia page provides the best context for resolving link and that straight forward inverse document frequency based scoring of anchor texts achieves around 4% less Mean Average Precision on the provided data set. © 2009 Springer Berlin Heidelberg.
    Original languageEnglish
    Title of host publicationAdvances in Focused Retrieval
    Subtitle of host publication7th International Workshop of the Initiative for the Evaluation of XML Retrieval, INEX 2008, Dagstuhl Castle, Germany, December 15-18, 2008. Revised and Selected Papers
    Place of PublicationBerlin, Heidelberg
    PublisherSpringer
    Pages354-365
    Number of pages12
    ISBN (Electronic)978-3-642-03761-0
    ISBN (Print)978-3-642-03760-3
    DOIs
    Publication statusPublished - 2009
    Event7th International Workshop of the Initiative for the Evaluation of XML Retrieval, INEX 2008 - Dagstuhl, Germany
    Duration: 15 Dec 200818 Dec 2008
    Conference number: 7

    Publication series

    NameLecture Notes in Computer Science
    PublisherSpringer
    Volume5631
    ISSN (Print)0302-9743
    ISSN (Electronic)1611-3349

    Workshop

    Workshop7th International Workshop of the Initiative for the Evaluation of XML Retrieval, INEX 2008
    Abbreviated titleINEX
    CountryGermany
    CityDagstuhl
    Period15/12/0818/12/08

      Fingerprint

    Keywords

    • Context Exploitation
    • INEX
    • Link-the-Wiki
    • Proximity
    • Suchmaschinen
    • XML mining
    • XML-Retrieval
    • Classification
    • Data mining
    • Information retrieval
    • Knowledge discovery
    • Large sets
    • p2p search
    • Performance evaluation
    • Similarity detection
    • Self organizing

    Cite this

    Granitzer, M., Seifert, C., & Zechner, M. (2009). Context based wikipedia linking. In Advances in Focused Retrieval: 7th International Workshop of the Initiative for the Evaluation of XML Retrieval, INEX 2008, Dagstuhl Castle, Germany, December 15-18, 2008. Revised and Selected Papers (pp. 354-365). (Lecture Notes in Computer Science; Vol. 5631). Berlin, Heidelberg: Springer. https://doi.org/10.1007/978-3-642-03761-0_36