Presentation 2004/11/27
Relevance Feedback Document Retrieval using Non-Relevant Documents(Text Mining I)(Joint Workshop of Vietnamese Society of AI, SIGKBS-JSAI, ICS-IPSJ, and IEICE-SIGAI on Active Mining)
TAKASHI ONODA, HIROSHI MURATA, SEIJI YAMADA,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) This paper reports a new document retrieval method using non-relevant documents. From a large data set of documents, we need to find documents that relate to human interesting in as few iterations of human testing or checking as possible. In each iteration a comparatively small batch of documents is evaluated for relating to the human interesting. This method is called relevance feedback. The relevance feedback needs a set of relevant and non-relevant documents. However, the initial presented documents which are checked by a user don't always include relevant documents. Accordingly we propose a feedback method using information of non-relevant documents only. We named this method non-relevance feedback. The irrelevance feedback selects a set of documents based on learning result by One-class SVM. Results from experiments show that this method is able to retrieve a relevant document from a set of non-relevant documents effectively.
Keyword(in Japanese) (See Japanese page)
Keyword(in English)
Paper # AI2004-20
Date of Issue

Conference Information
Committee AI
Conference Date 2004/11/27(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 ENG
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Relevance Feedback Document Retrieval using Non-Relevant Documents(Text Mining I)(Joint Workshop of Vietnamese Society of AI, SIGKBS-JSAI, ICS-IPSJ, and IEICE-SIGAI on Active Mining)
Sub Title (in English)
Keyword(1)
1st Author's Name TAKASHI ONODA
1st Author's Affiliation Central Research Institute of Electric Power Industry()
2nd Author's Name HIROSHI MURATA
2nd Author's Affiliation Central Research Institute of Electric Power Industry
3rd Author's Name SEIJI YAMADA
3rd Author's Affiliation National Institute of Informatics
Date 2004/11/27
Paper # AI2004-20
Volume (vol) vol.104
Number (no) 485
Page pp.pp.-
#Pages 6
Date of Issue