Presentation 2004/7/7
An automatic vectors creation method for metadata expression of semantic associative search
Kota TAKAMATSU, Yasushi KIYOKI,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) In this paper, we present an automatic creation method for metadata vectors according to feature words specified in an authorized dictionary. By our method, we can obtain a large number of metadata vectors for semantic search systems. Our method realizes automatic creation for metadata vectors as the following five steps: 1) extracting feature words from the target dictionary, 2) extracting basic words and explaining words from the dictionary, 3) applying noize redunction filters that normalize variants of expression, 4) creating word definitions according to feature words and explaining words, 5) converting explaining words, which have no corresponding feature words, by applying special filters. We clarify effectiveness of our method by applying to the semantic associative search method.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Establishment of a space / Automatic creation / Metadata / Semantic associative search
Paper # DE2004-67
Date of Issue

Conference Information
Committee DE
Conference Date 2004/7/7(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) An automatic vectors creation method for metadata expression of semantic associative search
Sub Title (in English)
Keyword(1) Establishment of a space
Keyword(2) Automatic creation
Keyword(3) Metadata
Keyword(4) Semantic associative search
1st Author's Name Kota TAKAMATSU
1st Author's Affiliation Keio University, Graduate School of Media and Governance()
2nd Author's Name Yasushi KIYOKI
2nd Author's Affiliation Keio University, Faculty of Environmental Information
Date 2004/7/7
Paper # DE2004-67
Volume (vol) vol.104
Number (no) 177
Page pp.pp.-
#Pages 6
Date of Issue