Integration of recursive structure of hopfield and ontologies for query expansion One of the ways to enhance the information retrieval performance is query expansion (QE) which means adding some terms to the query in order to reduce mismatch between information needs and retrieved documents. In this way “Query Drift” occurring for ambiguous queries is a common problem. Special case of this problem is “Outweighting” that usually occurs for long queries, that is, some augmented words strongly related to an individual query words but not to the all. In this paper we propose a new method for QE to reduce the effects of disambiguated query terms and decrease query drifting. In proposed method for word outweighting elimination, query terms are grouped based on their semantic relationships. For each group, candidates are fetched from WordNet that relates to the all of words group. Then by using recursive structure of Hopfield network words with the most relationship with other words are selected. Moreover, the Term Semantic Network has used to overcome some of the shortcomings of WordNet. Evaluation results on CACM and CERC test collections show that the proposed method is effective and improve 4% and 12% of Mean Average Precision respectively.