Ontology-based query processing for understanding intentions of indirect speech acts in natural-language question answering
by Hideki Mima, Susumu Ota, Koji Nagatsuna
International Journal of Computer Applications in Technology (IJCAT), Vol. 35, No. 2/3/4, 2009

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.

Online publication date: Sat, 20-Jun-2009

The full text of this article is only available to individual subscribers or to users at subscribing institutions.

 
Existing subscribers:
Go to Inderscience Online Journals to access the Full Text of this article.

Pay per view:
If you are not a subscriber and you just want to read the full contents of this article, buy online access here.

Complimentary Subscribers, Editors or Members of the Editorial Board of the International Journal of Computer Applications in Technology (IJCAT):
Login with your Inderscience username and password:

    Username:        Password:         

Forgotten your password?


Want to subscribe?
A subscription gives you complete access to all articles in the current issue, as well as to all articles in the previous three years (where applicable). See our Orders page to subscribe.

If you still need assistance, please email subs@inderscience.com