AKT EPrint Archive

LRD: Latent Relation Discovery for Vector Space Expansion and Information Retrieval

Authors UNSPECIFIED (2006) LRD: Latent Relation Discovery for Vector Space Expansion and Information Retrieval. In Gonçalves, Mr. Alexandre and Zhu, Dr. Jianhan and Song, Dr. Dawei and Uren, Dr. Victoria and Pacheco, Prof. Roberto, Eds. Proceedings The Seventh International Conference on Web-Age Information Management (WAIM 2006), Hong Kong, China.

This document is not available online.

In this paper, we propose a text mining method called LRD (latent relation discovery), which extends the traditional vector space model of document representation in order to improve information retrieval (IR) on documents and document clustering. Our LRD method extracts terms and entities, such as person, organization, or project names, and discovers relationships between them by taking into account their co-occurrence in textual corpora. Given a target entity, LRD discovers other entities closely related to the target effec-tively and efficiently. With respect to such relatedness, a measure of relation strength between entities is defined. LRD uses relation strength to enhance the vector space model, and uses the enhanced vector space model for query based IR on documents and clustering documents in order to discover complex rela-tionships among terms and entities. Our experiments on a standard dataset for query based IR shows that our LRD method performed significantly better than traditional vector space model and other five standard statistical methods for vector expansion.

Keywords:information retrieval, knowledge management, vector space, vector space expansion, relation strength, clustering
Subjects:AKT Challenges > Knowledge retrieval
AKT Challenges > Knowledge acquisition
ID Code:492
Deposited By:Zhu, Dr. Jianhan
Deposited On:31 March 2006

Contact the site administrator at: hg@ecs.soton.ac.uk