Automatic Generation of Information-seeking Questions Using Concept Clusters

One of the basic problems of efficiently generating information-seeking dialogue in interactive question answering is to find the topic of an information-seeking question with respect to the answer documents. In this paper we propose an approach to solving this problem using concept clusters. Our empirical results on TREC collections and our ambiguous question collection shows that this approach can be successfully employed to handle ambiguous and list questions.

• Type: Journal
• Year: 2009
• Where: ACL
• Authors: Shuguang Li, Suresh Manandhar
• Keywords: ACL 2009, Ambiguous Question, Computational Linguistics, Information-seeking Question, Interactive Question Answering