Sciweavers

NLPRS
2001
Springer

A Probabilistic Model for Japanese Zero Pronoun Resolution Integrating Syntactic and Semantic Features

14 years 4 months ago
A Probabilistic Model for Japanese Zero Pronoun Resolution Integrating Syntactic and Semantic Features
This paper proposes a method to resolve Japanese zero pronouns by identifying their antecedents. Our method uses a probabilistic model, which is decomposed into syntactic and semantic properties. A syntactic model is trained based on corpora annotated with anaphoric relations. However, a semantic model is trained based on a large-scale unannotated corpus, so as to counter the data sparseness problem. We also propose the notion of certainty to improve the accuracy of zero pronoun resolution. We show the effectiveness of our proposed method by way of experiments.
Kazuhiro Seki, Atsushi Fujii, Tetsuya Ishikawa
Added 30 Jul 2010
Updated 30 Jul 2010
Type Conference
Year 2001
Where NLPRS
Authors Kazuhiro Seki, Atsushi Fujii, Tetsuya Ishikawa
Comments (0)