Presentation 2006-07-13
Person Identification by Proper Noun Clauses on the Web
Naoki MUKAIDA, Keishi TAJIMA,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) When we retrieve Web pages by using a person name as query keywords, the result often includes pages about other persons of the same name. One well-known approach to this problem is to classify the result pages into page groups corresponding to those persons with the same name by using clustering techniques based on the page contents to the search result. In this paper, we propose a method to improve the accuracy of such clustering by giving bigger weight values to the proper noun clauses related to the target person, and also propose a method to discover such related proper noun clauses appearing in the search results.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Web retrieval / information retrieval / query by pserson name / person identification / object identification
Paper # DE2006-76
Date of Issue

Conference Information
Committee DE
Conference Date 2006/7/6(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) Person Identification by Proper Noun Clauses on the Web
Sub Title (in English)
Keyword(1) Web retrieval
Keyword(2) information retrieval
Keyword(3) query by pserson name
Keyword(4) person identification
Keyword(5) object identification
1st Author's Name Naoki MUKAIDA
1st Author's Affiliation School of Information Science, Japan Advanced Institute of Science And Technology()
2nd Author's Name Keishi TAJIMA
2nd Author's Affiliation School of Information Science, Japan Advanced Institute of Science And Technology:Graduate School of Informatics, Kyoto University
Date 2006-07-13
Paper # DE2006-76
Volume (vol) vol.106
Number (no) 149
Page pp.pp.-
#Pages 6
Date of Issue