Presentation 2003/10/30
Japanese Text Extraction using the Dependency Tree(Natural Language Understanding and Models of Communication)
Jun ITO, Tetsuya SAKAI, Shigeichi HIRASAWA,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) A Japanese sentence can be expressed as a tree structure (dependency tree) based on dependency relations. Since a subtree of a dependency tree preserves the dependency relations of the original tree, it generally represents a correct sentence on its own. In this paper, a document is expressed as an extended dependency tree, in which weights are assigned to its nodes and edges. Moreover, the problem of extracting important text fragments is formalized as that of "searching for a subtree that maximizes a certain score from subtrees of the extended decision tree". We implemented such a summarization system and performed evaluations based on manual assessment as well as comparison with original texts.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) automatic summarization / text extraction / dependency tree / search of the optimal partial tree
Paper # NLC2003-28
Date of Issue

Conference Information
Committee NLC
Conference Date 2003/10/30(1days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair
Vice Chair
Secretary
Assistant

Paper Information
Registration To Natural Language Understanding and Models of Communication (NLC)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Japanese Text Extraction using the Dependency Tree(Natural Language Understanding and Models of Communication)
Sub Title (in English)
Keyword(1) automatic summarization
Keyword(2) text extraction
Keyword(3) dependency tree
Keyword(4) search of the optimal partial tree
1st Author's Name Jun ITO
1st Author's Affiliation Department of Indudtrial and Management System Engineering, School of Science and Engineering Waseda University()
2nd Author's Name Tetsuya SAKAI
2nd Author's Affiliation Knowledge Media Laboratory, Toshiba Corporate RD Center
3rd Author's Name Shigeichi HIRASAWA
3rd Author's Affiliation Department of Indudtrial and Management System Engineering, School of Science and Engineering Waseda University
Date 2003/10/30
Paper # NLC2003-28
Volume (vol) vol.103
Number (no) 407
Page pp.pp.-
#Pages 6
Date of Issue