Presentation 1999/7/22
NetNews Area Analysis Using Surface Information
Hisako Asano, Masaaki Nagata,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) For information extraction and summarization of NetNews and e-mails, it is necessary that the structure of these electronic texts are analyzed previously because they are not structured and exist extra character usage such as quotation marks (e.g. "> "). We propose a method which analyzes quotation structure and area classification by contents - text by sender, text by news-reader and signature - using decision trees which have surface information as properties. Experiments using our NetNews corpus shows that this method is effective.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Area structure analysis / NetNews / XML / C4.5 / Decision tree
Paper # NLC99-9
Date of Issue

Conference Information
Committee NLC
Conference Date 1999/7/22(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) NetNews Area Analysis Using Surface Information
Sub Title (in English)
Keyword(1) Area structure analysis
Keyword(2) NetNews
Keyword(3) XML
Keyword(4) C4.5
Keyword(5) Decision tree
1st Author's Name Hisako Asano
1st Author's Affiliation NTT CyberSpace Laboratories()
2nd Author's Name Masaaki Nagata
2nd Author's Affiliation NTT CyberSpace Laboratories
Date 1999/7/22
Paper # NLC99-9
Volume (vol) vol.99
Number (no) 227
Page pp.pp.-
#Pages 8
Date of Issue