Zero-anaphora resolution by learning rich syntactic pattern features

Ryu Iida, Kentaro Inui, Yuji Matsumoto

Research output: Contribution to journalArticle

24 Citations (Scopus)

Abstract

We approach the zero-anaphora resolution problem by decomposing it into intrasentential and intersentential zero-anaphora resolution tasks. For the former task, syntactic patterns of zeropronouns and their antecedents are useful clues. Taking Japanese as a target language, we empirically demonstrate that incorporating rich syntactic pattern features in a state-of-the-art learning-based anaphora resolution model dramatically improves the accuracy of intrasentential zero-anaphora, which consequently improves the overall performance of zero-anaphora resolution.

Original languageEnglish
Article number12
JournalACM Transactions on Asian Language Information Processing
Volume6
Issue number4
DOIs
Publication statusPublished - 2007 Dec 1
Externally publishedYes

Keywords

  • Anaphora resolution
  • Zero-pronouns

ASJC Scopus subject areas

  • Computer Science(all)

Fingerprint Dive into the research topics of 'Zero-anaphora resolution by learning rich syntactic pattern features'. Together they form a unique fingerprint.

Cite this