Query Reformulation for Task-Oriented Web Searches

Web searches are driven by information needs and intend the accomplishment of specific tasks. Information needs are determined by the topical subject of queries, i.e. what we search, while tasks are determined by the user motives that induce the submission of queries, i.e. why we search. Though there exist numerous studies on how to assist searchers specify queries that are expressive of their underlying information needs, little has been done to help searchers specify queries that describe the tasks they pursue via their searches. In this paper we propose a query reformulation method to empower task-oriented web searches. Given a query, our method starts with the identification of terms that could serve as descriptors of the potential search tasks the query represents. Based on the identified terms, it generates query re-formulations that explicitly verbalize the possible search tasks. Query reformulations are presented to the user in order to select the one that best suits her search intention.