Category oriented task extraction

With increasing amounts of digital content, users can accomplish complex tasks online, thus making task extraction from query logs an active area of research. Recently, some approaches have proposed entity based extraction of tasks, where they either use entities as features or construct task dictionaries that contain multiple tasks. While text based features do not exploit entities directly, task dictionaries do not provide concise or distinct representation of tasks. We overcome these shortcomings by extracting category oriented tasks by exploiting properties of an existing, publicly available category hierarchy. We evaluate quality of these tasks with implicit, explicit and application based evaluation. Empirical evaluation shows that category based task extraction results in more accurate and useful tasks.