Boosting Passage Retrieval through Reuse in Question Answering



Question Answering (QA) is an emerging important field in Information Retrieval. In a QA system the archive of previous questions asked from the system makes a collection full of useful factual nuggets. This paper makes an initial attempt to investigate the reuse of facts contained in the archive of previous questions to help and gain performance in answering future related factoid questions. It models the role of facts in questions through discourse transition of user question answering process, and presents approaches to identify and extract these facts with the help of lexical semantic resources. Strategies to implement the reuse of facts to boost query generation in the passage retrieval stage of a QA system as well as ideas on system evaluation are discussed.