UPM Institutional Repository

A bayesian approach to intention-based response generation


Citation

Mustapha, Aida and Sulaiman, Md. Nasir and Mahmod, Ramlan and Selamat, Mohd. Hasan (2009) A bayesian approach to intention-based response generation. European Journal of Scientific Research, 32 (4). pp. 477-489. ISSN 1450216X

Abstract

The statistical approach to natural language generation of overgeneration-andranking suffers from expensive over generation. This article reports the findings of response classification experiment in the new approach of intention-based classification-andranking. Possible responses are deliberately chosen from a dialogue corpus rather than wholly generated, so the approach allows short ungrammatical utterances as long as they satisfy the intended meaning of the input utterance. We hypothesize that a response is relevant when it satisfies the intention of the preceding utterance, therefore this approach highly depends on intentions, rather than syntactic characterization of input utterance. The response classification experiment is tested on a mixed-initiative, transaction dialogue corpus in the theater domain. This article reports a promising start of 73% accuracy in prediction of response classes in a classification experiment with application of Bayesian networks.


Download File

[img]
Preview
PDF (Abstract)
A bayesian approach to intention.pdf

Download (83kB) | Preview

Additional Metadata

Item Type: Article
Subject: Bayesian statistical decision theory
Subject: Mathematical optimization
Subject: Expert systems (Computer science)
Divisions: Faculty of Computer Science and Information Technology
Publisher: EuroJournals Publishing, Inc.
Keywords: Bayesian Networks, Classification, Dialogue Systems, Natural Language
Depositing User: Umikalthom Abdullah
Date Deposited: 22 Nov 2011 01:08
Last Modified: 23 Oct 2015 02:17
URI: http://psasir.upm.edu.my/id/eprint/12647
Statistic Details: View Download Statistic

Actions (login required)

View Item View Item