Title: Ontology-based query processing for understanding intentions of indirect speech acts in natural-language question answering
Authors: Hideki Mima, Susumu Ota, Koji Nagatsuna
Addresses: School of Engineering, University of Tokyo, 7-3-1 Hongou, Bunkyouku, Tokyo 113-8656, Japan. ' School of Engineering, University of Tokyo, 7-3-1 Hongou, Bunkyouku, Tokyo 113-8656, Japan. ' School of Engineering, University of Tokyo, 7-3-1 Hongou, Bunkyouku, Tokyo 113-8656, Japan
Abstract: In an attempt to develop a robust method for achieving natural-language question answering, we propose a method for ontology-based query processing to infer intentions from indirect speech acts that do not express the real intentions explicitly. In this method, the real intentions of the indirect speech act are classified into one of five intention classes such as |refusal| and |reversal|. Furthermore, we construct an ontology for intention transition, which is composed of concepts for events and their relations attributed with the above intention classes. In addition, we construct an ontology of objects for the targets of events – e.g. |files| and |figures|, which also contains special relations such as |exclusive|. Given the two above ontologies, an algorithm is proposed to infer users| actual intentions. This proposed method was tested with human subjects and a prototype system. The system successfully inferred the intentions for approximately 80% of the subjects| indirect speech acts.
Keywords: natural language question answering; indirect speech; ontology; query processing; implicit intentions; intention inference.
International Journal of Computer Applications in Technology, 2009 Vol.35 No.2/3/4, pp.271 - 280
Available online: 20 Jun 2009 *Full-text access for editors Access for subscribers Purchase this article Comment on this article