Zero pronoun resolution based on automatically constructed case frames and structural preference of antecedents

Daisuke Kawahara, Sadao Kurohashi

Research output: Contribution to journalConference article

1 Citation (Scopus)

Abstract

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%.

Original languageEnglish
Pages (from-to)12-21
Number of pages10
JournalLecture Notes in Artificial Intelligence (Subseries of Lecture Notes in Computer Science)
Volume3248
Publication statusPublished - 2005
Externally publishedYes
EventFirst International Joint Conference on Natural Language Processing - IJCNLP 2004 - Hainan Island, China
Duration: 2004 Mar 222004 Mar 24

ASJC Scopus subject areas

  • Theoretical Computer Science
  • Computer Science(all)

Fingerprint Dive into the research topics of 'Zero pronoun resolution based on automatically constructed case frames and structural preference of antecedents'. Together they form a unique fingerprint.

  • Cite this