User behaviors lend a helping hand: Learning paraphrase query patterns from search log sessions

Search log sessions contain a large number of paraphrases contributed by users during query rewriting. However, it is a big challenge to distinguish paraphrases from the simply related queries in the sessions. This paper addresses this problem by making innovative use of user behavior information embodied in query sessions. Specifically, we learn paraphrase patterns from the search log sessions with a classification framework, in which three types of user behavior features are exploited besides the conventional features. We evaluate the method using a query log of a commercial search engine. Experimental results demonstrate the effectiveness of our method, especially the significant contribution of the user behavior features. We extract over 250,000 pairs of paraphrase patterns from the used search log, with a precision over 76%.