Zero Pronoun Resolution Based on Automatically Constructed Case Frames and Structural Preference of Antecedents

  • Daisuke Kawahara
  • Sadao Kurohashi
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3248)


This paper describes a method to detect and resolve zero pronouns in Japanese text. We detect zero pronouns by case analysis based on automatically constructed case frames, and select their appropriate antecedents based on similarity to examples in the case frames. We also introduce structural preference of antecedents to precisely capture the tendency that a zero pronoun has its antecedent in its close position. Experimental results on 100 articles indicated that the precision and recall of zero pronoun detection is 87.1% and 74.8% respectively and the accuracy of antecedent estimation is 61.8%.


Structural Preference Liberal Democratic Party Location Class Main Clause Subordinate Clause 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    McCarthy, J.F., Lehnert, W.G.: Using decision trees for coreference resolution. In: Proceedings of the 14th International Joint Conference on Artificial Intelligence, pp. 1050–1055 (1995)Google Scholar
  2. 2.
    Murata, M., Isahara, H., Nagao, M.: Pronoun resolution in Japanese sentences using surface expressions and examples. In: Proceedings of the ACL 1999 Workshop on Coreference and Its Applications, pp. 39–46 (1999)Google Scholar
  3. 3.
    Soon, W.M., Ng, H.T., Lim, D.C.Y.: A machine learning approach to coreference resolution of noun phrases. Computational Linguistics 27, 521–544 (2001)CrossRefGoogle Scholar
  4. 4.
    Kawahara, D., Kurohashi, S.: Fertilization of case frame dictionary for robust Japanese case analysis. In: Proceedings of the 19th International Conference on Computational Linguistics, pp. 425–431 (2002)Google Scholar
  5. 5.
    Seki, K., Fujii, A., Ishikawa, T.: A probabilistic method for analyzing Japanese anaphora integrating zero pronoun detection and resolution. In: Proceedings of the 19th International Conference on Computational Linguistics, pp. 911–917 (2002)Google Scholar
  6. 6.
    Aone, C., Bennett, S.W.: Evaluating automated and manual acquisition of anaphora resolution strategies. In: Proceedings of the 33rd Annual Meeting of the Association for Computational Linguistics, pp. 122–129 (1995)Google Scholar
  7. 7.
    Kurohashi, S., Nagao, M.: A method of case structure analysis for japanese sentences based on examples in case frame dictionary. IEICE Transactions on Information and Systems E77-D(2) (1994)Google Scholar
  8. 8.
    Kawahara, D., Kurohashi, S., Hasida, K.: Construction of a Japanese relevancetagged corpus. In: Proceedings of the 3rd International Conference on Language Resources and Evaluation, pp. 2008–2013 (2002)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2005

Authors and Affiliations

  • Daisuke Kawahara
    • 1
  • Sadao Kurohashi
    • 1
  1. 1.University of TokyoTokyoJapan

Personalised recommendations