A relevance-based superimposition model for effective information retrieval

Semantic ambiguity is a serious problem in information retrieval. Query expansion has been proposed as one method of solving this problem. However, queries tend not to have much information for fitting query vectors to the latent semantics, which are difficult to express in a few query terms given by users. We propose a document vector modification method that modifies document vectors based on the relevance of documents. This method is expected to show better retrieval effectiveness than conventional methods. Tn this paper, we evaluate our method through retrieval experiments in which the relevance of documents extracted from scientific papers is assessed, and a comparison with tf.idfis described.