Related Queries Recommendation Based on User Logs for Chinese Search Engines

This paper presents an effective method to suggest a list of semantically related queries to a given query submitted to a search engine. The related queries are based on previous queries in the user logs, and can be issued by the user to rephrase the search process. The method proposed is based on a query clustering process in which groups of semantically similar queries are identified. An efficient clustering algorithm called suffix tree clustering is developed in the study. Meanwhile, the keyword- based similarity measure is used for determining the closest cluster to the given query, and the Chinese synonymy is also considered in the measure to increase the veracity. To evaluate the proposed method, a series of experiments are carried out by using one month user logs from Chinese search engine Sogou. The performed experiments verify the effectiveness and efficiency of the method for query recommendation.