Distributed Representations for Semantic Matching in non-factoid Question Answering

Users’ interactions with search engines is shifting towards more complex information needs and the need for a deeper semantic understanding of the query intent is needed. In this paper we propose a novel semantic matching criterion that adopts distributed representations of words in order to address complex information needs in a scalable way. We show that combining this criterion with other well established features it is possible to obtain over 22% improvement for MRR and 27% in P@1 over the best performing approach for answering non-factoid questions, a specific form of complex information need. Moreover we show that in our setting our criterion can substitute more complex linguistic feature.