Do We Need Entity-Centric Knowledge Bases for Entity Disambiguation?

Stefan Zwicklbauer, Christin Seifert, Michael Granitzer

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

    1 Citation (Scopus)

    Abstract

    Entity Disambiguation has been studied extensively in the last 10 years with authors reporting increasingly well per- forming systems. However, most studies focused on gen- eral purpose knowledge bases like Wikipedia or DBPedia and left out the question how those results generalize to more specialized domains. This is especially important in the context of Linked Open Data which forms an enormous resource for disambiguation. However, the influence of do- main heterogeneity, size and quality of the knowledge base remains largely unanswered. In this paper we present an extensive set of experiments on special purpose knowledge bases from the biomedical domain where we evaluate the disambiguation performance along four variables: (i) the representation of the knowledge base as being either entity- centric or document-centric, (ii) the size of the knowledge base in terms of entities covered, (iii) the semantic het- erogeneity of a domain and (iv) the quality and complete- ness of a knowledge base. Our results show that for spe- cial purpose knowledge bases (i) document-centric disambig- uation significantly outperforms entity-centric disambigua- tion, (ii) document-centric disambiguation does not depend on the size of the knowledge-base, while entity-centric ap- proaches do, and (iii) disambiguation performance varies greatly across domains. These results suggest that domain- heterogeneity, size and knowledge base quality have to be carefully considered for the design of entity disambiguation systems and that for constructing knowledge bases user- annotated texts are preferable to carefully constructed know- ledge bases.
    Original languageEnglish
    Title of host publicationi-Know'13. Proceedings of the 13th International Conference on Knowledge Management and Knowledge Technologies - i-Know '13
    Place of PublicationNew York
    PublisherACM Press
    Number of pages8
    ISBN (Print)9781450323000
    DOIs
    Publication statusPublished - 2013
    Event13th International Conference on Knowledge Management and Knowledge Technologies - Graz, Austria
    Duration: 4 Sep 20136 Sep 2013
    Conference number: 13

    Conference

    Conference13th International Conference on Knowledge Management and Knowledge Technologies
    Abbreviated titlei-KNOW 2013
    CountryAustria
    CityGraz
    Period4/09/136/09/13

    Fingerprint Dive into the research topics of 'Do We Need Entity-Centric Knowledge Bases for Entity Disambiguation?'. Together they form a unique fingerprint.

  • Cite this

    Zwicklbauer, S., Seifert, C., & Granitzer, M. (2013). Do We Need Entity-Centric Knowledge Bases for Entity Disambiguation? In i-Know'13. Proceedings of the 13th International Conference on Knowledge Management and Knowledge Technologies - i-Know '13 [4] New York: ACM Press. https://doi.org/10.1145/2494188.2494198