Paper: Exact Phrases in Information Retrieval for Question Answering

ACL ID W08-1802
Title Exact Phrases in Information Retrieval for Question Answering
Venue Coling 2008: Proceedings of the workshop on Human Judgements in Computational Linguistics
Year 2008

Question answering (QA) is the task of finding a concise answer to a natural lan- guage question. The first stage of QA in- volves information retrieval. Therefore, performance of an information retrieval subsystem serves as an upper bound for the performance of a QA system. In this work we use phrases automatically identified from questions as exact match constituents to search queries. Our results show an im- provement over baseline on several docu- ment and sentence retrieval measures on the WEB dataset. We get a 20% relative improvement in MRR for sentence extrac- tion on the WEB dataset when using au- tomatically generated phrases and a fur- ther 9.5% relative improvement when us- ing manually annotated phrases. Surpris- ingly, a separate experiment on the indexed AQUAINT dataset show...