Paper: Going Beyond Traditional QA Systems: Challenges and Keys in Opinion Question Answering

ACL ID C10-2004
Title Going Beyond Traditional QA Systems: Challenges and Keys in Opinion Question Answering
Venue International Conference on Computational Linguistics
Session Poster Session
Year 2010
Authors

The treatment of factual data has been widely studied in different areas of Nat- ural Language Processing (NLP). How- ever, processing subjective information still poses important challenges. This paper presents research aimed at assess- ing techniques that have been suggested as appropriate in the context of subjec- tive - Opinion Question Answering (OQA). We evaluate the performance of an OQA with these new components and propose methods to optimally tackle the issues encountered. We assess the impact of including additional resources and processes with the purpose of im- proving the system performance on two distinct blog datasets. The improve- ments obtained for the different combi- nation of tools are statistically signifi- cant. We thus conclude that the pro- posed appro...