Presentation 1998/5/21
A Study of Bayesian Clustering of Document Set Based on GA
Keiko AOKI, Kazunori MATSUMOTO, Keiichiro HOASHI, Kazuo HASHIMOTO,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) In order to reduce calculations in Bayesian clustering of document set, we introduce an algorithm to decide a semi-optimal cluster by GA, whose genes encode cluster structures. The proposed method uses Minimum Description Length (MDL) of clusters for the evaluation of candidate genes. We compare the performance of the proposed algorithm with those of a conventional Bayesian clustering algorithm and a semi-optimal algorithm known as"topdown clustering". The empirical result shows the accuracy of proposed method for document retrieval is better than that of topdown clustering. It proves the effectiveness of a search based on GA.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Text / Bayesian Clustering / GA / Hispeed
Paper #
Date of Issue

Conference Information
Committee AI
Conference Date 1998/5/21(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 Artificial Intelligence and Knowledge-Based Processing (AI)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) A Study of Bayesian Clustering of Document Set Based on GA
Sub Title (in English)
Keyword(1) Text
Keyword(2) Bayesian Clustering
Keyword(3) GA
Keyword(4) Hispeed
1st Author's Name Keiko AOKI
1st Author's Affiliation KDD R&D Laboratories()
2nd Author's Name Kazunori MATSUMOTO
2nd Author's Affiliation KDD R&D Laboratories
3rd Author's Name Keiichiro HOASHI
3rd Author's Affiliation KDD R&D Laboratories
4th Author's Name Kazuo HASHIMOTO
4th Author's Affiliation KDD R&D Laboratories
Date 1998/5/21
Paper #
Volume (vol) vol.98
Number (no) 58
Page pp.pp.-
#Pages 7
Date of Issue