Query expansion with statistical machine translation

In practical applications of information retrieval, such as the search engine, the query user submitted contains only several keywords usually. This will cause unmatched issues of words between relevant files and the user's query, and result in more seriously negative effects on the performance of information retrieval. On the basis of analyzing the process of producing query, this paper puts forward a new method of query expansion based on the model of statistical machine translation. The approach extract related terms between documents and query through statistical machine translation model, then expand the query with them. The experiment on TREC data collection shows that our method achieved 4 - 17% of the improvement all the time more than the language model method without expanding. Compared to pseudo feedback, our method has the competitive average precision.