Presentation 2008/7/10
Sentence Compression by Removing Recursive Structure from Parse Tree
Seiji EGAWA, Yoshihide KATO, Shigeki MATSUBARA,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) Sentence compression is a task of generating a grammatical short sentence from an original sentence, retaining the most important information. The existing methods of only removing the constituents in the parse tree of an original sentence cannot emulate human compression which changes structures of the parse tree. This paper proposes a method to remove recursive structures, one of such structural conversions, and generate a grammatical short sentence. In order to remove a recursive structure, our method detects the constituents forming the structure and remove them as a unit. Compression experiments have shown that our method generates more grammatical compressed sentences than the previous method.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) text summarization / phrase structure / maximum entropy method / text corpus
Paper # NLC2008-11
Date of Issue

Conference Information
Committee NLC
Conference Date 2008/7/10(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) Sentence Compression by Removing Recursive Structure from Parse Tree
Sub Title (in English)
Keyword(1) text summarization
Keyword(2) phrase structure
Keyword(3) maximum entropy method
Keyword(4) text corpus
1st Author's Name Seiji EGAWA
1st Author's Affiliation Graduate School of Information Science, Nagoya University()
2nd Author's Name Yoshihide KATO
2nd Author's Affiliation Graduate School of International Development, Nagoya University
3rd Author's Name Shigeki MATSUBARA
3rd Author's Affiliation Information Technology Center, Nagoya University
Date 2008/7/10
Paper # NLC2008-11
Volume (vol) vol.108
Number (no) 141
Page pp.pp.-
#Pages 6
Date of Issue