BDBComp
Parceria:
SBC
Modelagem vetorial estendida por regras de associação

Bruno PossasWagner MeiraNivio ZivianiBerthier Ribeiro-Neto

The goal of this work is to present an extension to the vector model that accounts for the correlation among query terms, by using association rules, a popular data mining technique. In Information Retrieval, the vector model allows retrieving a set of documents from a term-based query, where both query terms and documents are vectors in a vector space. Although the vector model has been used succesfully for decades, there are no practical and ef?cient mechanisms that account for correlations among query terms in each document from the collection until now. The novelty of this work is the proposal of a method for computing the correlations among query terms. The changes to the original vector model are minimal, and experimental results show that our extended vector model enhances the precision of the results for all the collections evaluated.

http://www.lbd.dcc.ufmg.br:8080/colecoes/sbbd/2001/005.pdf

Caso o link acima esteja inválido, faça uma busca pelo texto completo na Web: Buscar na Web

Biblioteca Digital Brasileira de Computação - Contato: bdbcomp@lbd.dcc.ufmg.br
     Mantida por:
LBD