• DocumentCode
    660909
  • Title

    Improving Entity Linking Performance Using Frame Semantics

  • Author

    Nural, Mustafa V. ; Miller, John A. ; Arpinar, I. Budak

  • Author_Institution
    Dept. of Comput. Sci., Univ. of Georgia, Athens, GA, USA
  • fYear
    2013
  • fDate
    16-18 Sept. 2013
  • Firstpage
    56
  • Lastpage
    63
  • Abstract
    In this paper, we investigate the use of Frame Semantics for improving the performance of linking of non-PLO (Person, Location, Organization) entities to Wikipedia articles. We propose an architecture for a system using Frame Semantics and Selectional Preferences (SP) to improve precision of linking non-PLO entities. We present performance results, which suggest that our system provides a mechanism to improve entity linking for non-PLO entities. We also show that Selectional Preferences can contribute for improved entity linking.
  • Keywords
    Web sites; text analysis; SP; Wikipedia articles; entity linking performance; frame semantics; nonPLO entities; nonlocation entity; nonorganization entity; nonperson entity; selectional preferences; text annotation; Electronic publishing; Encyclopedias; Internet; Joining processes; Labeling; Semantics; Entity Disambiguation; Entity Linking; Frame Semantics; Selectional Preferences; Semantic Role Labeling;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Semantic Computing (ICSC), 2013 IEEE Seventh International Conference on
  • Conference_Location
    Irvine, CA
  • Type

    conf

  • DOI
    10.1109/ICSC.2013.19
  • Filename
    6693494