Presentation 2002/7/10
Extract Event Information From HTML Documents
Shinji MIYAKE, Kazumitsu OKABE, Hidetomo TORIGOE, Kazumasa YOKOTA,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) In this paper, we describe a method of extracting event information from HTML documents, and discuss some problems involved in the method. In order to extract event information, specification of event information area, specification of required terms and extraction, and supplement of insufficient terms are required. For this reason, analysis of structure information of a HTML document, pattern matching for tag and data area, and conversion of values are performed. Various kinds of event information are extracted from HTML documents. This method increases the availability of HTML information by extracting records in the same form from HTML documents.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) HTML / Information Extraction / Event Information / Information Integration
Paper # DE2002-16
Date of Issue

Conference Information
Committee DE
Conference Date 2002/7/10(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 Data Engineering (DE)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Extract Event Information From HTML Documents
Sub Title (in English)
Keyword(1) HTML
Keyword(2) Information Extraction
Keyword(3) Event Information
Keyword(4) Information Integration
1st Author's Name Shinji MIYAKE
1st Author's Affiliation Ryobi Systems Corporation, Software Company:Okayama Prefectural University, Graduate course of Information Science and System Engineering()
2nd Author's Name Kazumitsu OKABE
2nd Author's Affiliation Ryobi Systems Corporation, Software Company:Okayama Prefectural University, Graduate course of Information Science and System Engineering
3rd Author's Name Hidetomo TORIGOE
3rd Author's Affiliation Takuma National College of Technology:Okayama Prefectural University, Graduate course of Information Science and System Engineering
4th Author's Name Kazumasa YOKOTA
4th Author's Affiliation Okayama Prefectural University, Faculty of Information Science and System Engineering
Date 2002/7/10
Paper # DE2002-16
Volume (vol) vol.102
Number (no) 207
Page pp.pp.-
#Pages 6
Date of Issue