Query expansion based on term similarity tree model

We propose a new method for query expansion called "term similarity tree model" (TSTM). Term similarity tree is built to represent and estimate similarities between terms. Based on TSTM, we use similarity restriction and overlay restriction to implement query expansion. This method can cluster terms automatically, make the process of query expansion more flexible and controllable, and control noise effectively. In addition, the parameters of TSTM can be adjusted easily to meet the requirements of different types of queries. TREC data is used to test the method. The experiments show that TSTM method outperforms the existing methods in query expansion, such as WordNet-based method, local cooccurrence method and latent semantic indexing (LSI-based) method.