Concept Tree Based Information Retrieval Model

Journal of Multimedia

关键词: Information Retrieval;    Query Expansion;    Markov Networks;    Concept Tree;   

Others  :  964688
DOI  :  10.4304/jmm.9.5.652-659

【 摘 要 】

This paper proposes a novel concept-based query expansion technique named Markov concept tree model (MCTM), discovering term relationship through the concept tree deduced by term markov network. We address two important issues for query expansion: the selection and the weighting of expansion search terms. In contrast to earlier methods, queries are expanded by adding those terms that are most similar to the concept of the query, rather than selecting terms that are similar to a signal query terms. Utilizing Markov network which is constructed according to the co-occurrence information of the terms in collection, it generate concept tree for each original query term, remove the redundant and irrelevant nodes in concept tree, then adjust the weight of original query and the weight of expansion term based on a pruning algorithm. We use this model for query expansion and evaluate the effectiveness of the model by examining the accuracy and robustness of the expansion methods, Compared with the baseline model, the experiments on standard dataset reveal that this method can achieve a better query quality

【 授权许可】

   
@ 2006-2014 by ACADEMY PUBLISHER – All rights reserved.