Presentation 2000/7/19
Retrieval Effectiveness for English Text Using the Relevance-based Superimposition Model
Teruhito KANAZAWA, Atsuhiro TAKASU, Jun ADACHI,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) We have proposed a Relevance-based Superimposition(RS) model to solve the problems of semantic ambiguity on information retrieval. This method partitions the documents so that the relevant documents fall into the same cluster based on the keywords given by authors, and it enables more accurate estimation of the weights of index terms than conventional methods such as tf・idf. We evaluated our method and showed the effectiveness of it using the NTCIR-1, which is a large-scale test collection for information retrieval. In this paper, we evaluate the proposed method using the TREC test collection, and examine the relation of the retrieval effectiveness of the proposed method to the kind of language and the characteristic of documents and queries.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) information retrieval / vector space model / document vector modification / RS model / TREC / NTCIR
Paper # DE2000-30
Date of Issue

Conference Information
Committee DE
Conference Date 2000/7/19(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) Retrieval Effectiveness for English Text Using the Relevance-based Superimposition Model
Sub Title (in English)
Keyword(1) information retrieval
Keyword(2) vector space model
Keyword(3) document vector modification
Keyword(4) RS model
Keyword(5) TREC
Keyword(6) NTCIR
1st Author's Name Teruhito KANAZAWA
1st Author's Affiliation Graduate School of Engineering, University of Tokyo()
2nd Author's Name Atsuhiro TAKASU
2nd Author's Affiliation NII(National Institute of Informatics)
3rd Author's Name Jun ADACHI
3rd Author's Affiliation NII(National Institute of Informatics)
Date 2000/7/19
Paper # DE2000-30
Volume (vol) vol.100
Number (no) 226
Page pp.pp.-
#Pages 8
Date of Issue