Query suggestion Based on the Query semantics and Clickthrough Data

Query suggestion plays an important role in improving the usability of search engines. For a given query raised by a specific user, the query suggestion technique aims at recommending relevant queries which may suit user's potential information needs. Due to the complexity of Web structure and the ambiguity of users' inputs query, most of existing suggestion algorithms suffer from the problem of poor recommendation accuracy. In this paper, aiming at providing semantically relevant queries for users, we develop a novel, effective and efficient query suggestion model by the query semantics and clickthrough data. First, we propose a method which combines query similarity with query semantics information, and calculates subject relevance among queries by word frequency information and the word's concept of Knowledge Network (HowNet). Second we propose another method which utilizes bipartite graph (query-URL bipartite graph) to learn the low-rank query feature space, and then builds a query similarity matrix model based on the features. Based on these, we design a ranking algorithm to propagate similarities on users' query log information, and finally recommend semantically relevant queries to users. Empirical experiments on the clickthrough data of a commercial search engine have proved the effectiveness and the efficiency of our method.