Home // ICDS 2014, The Eighth International Conference on Digital Society // View article

A Dependency Parsing Method Based on the Hierarchical Structure in Japanese Language

Authors:
Kazuki Ono
Kenji Hatano

Keywords: Dependency Parsing; Syntax Analysis; Syntax Tree Modeling

Abstract:
In this paper, we propose a new statistical dependency parsing method in Japanese language based on an extended hierarchical language model. Conventional Japanese statistical dependency parsers are primarily based on the bi-nominal dependency model between phrases, which has a limitation related to the order of phrases. Accordingly, the length of the phrase, which depends of dependency is limited by this limitation, the model is lacking. We propose a dependency model in Japanese language that considers the order of phrases based on the hierarchical Pitman-Yor process in order to overcome this limitation. Consequently, compared with conventional methods, our method can parse dependencies in long and complex Japanese sentences relatively well.

Pages: 203 to 208

Copyright: Copyright (c) IARIA, 2014

Publication date: March 23, 2014

Published in: conference

ISSN: 2308-3956

ISBN: 978-1-61208-324-7

Location: Barcelona, Spain

Dates: from March 23, 2014 to March 27, 2014