Home   >   CSC-OpenAccess Library   >    Manuscript Information
Full Text Available

This is an Open Access publication published under CSC-OpenAccess Policy.
Intention-Based Ranking for Surface Realization in Dialogue Systems
Aida Mustapha, MD. Nasir Sulaiman, Ramlan Mahmod, Mohd. Hasan Selamat
Pages - 175 - 185     |    Revised - 05-08-2009     |    Published - 01-09-2009
Volume - 3   Issue - 3    |    Publication Date - June 2009  Table of Contents
Natural Language Generation, Dialogue Systems, Intention
A new intention-based ranking is proposed to cater for intentionality in ranking dialogue utterances, as opposed to surface-based ranking using surface linguistic features in utterances. This is because utterances may be in the form of a sentence, a phrase, or just a word; hence basis for ranking must be on assessment of intentions, regardless of length of utterance and grammar rules. Intention-based ranking model is tested and compared with surface-based models on 15 response classes in theater domain. The results from comparative experiments show consistent accuracy distribution in intention-based ranking across all response classes with average of 91%. On the contrary, ranking accuracy for surface-based ranking is not uniform across the response classes, showing the dependency on surface representation of utterances in individual response class.
CITED BY (0)  
1 Google Scholar
2 Academic Journals Database
3 ScientificCommons
4 Academic Index
5 CiteSeerX
6 refSeek
8 Socol@r
9 ResearchGATE
10 Libsearch
11 Scribd
12 WorldCat
13 SlideShare
15 PdfSR
16 Chinese Directory Of Open Access
1 I. Langkilde and K. Knight. “Generation that exploits corpus-based statistical knowledge”. In Proceedings of the 36th Annual Meeting on Association for Computational Linguistics, Montreal, Quebec, Canada, 1998.
2 I. Langkilde. “Forest-based statistical sentence generation”. In Proceedings of the North American Meeting of the Association for Computational Lingustics, 2000.
3 I. Langkilde. “HALOGEN: A Foundation for General-Purpose Natural Language Generation: Sentence Realization Using Probabilistic Models of Language”. Ph.D. thesis, Information Science Institute, USC School of Engineering, 2002.
4 S. Bangalore and O. Rambow. “Exploiting a probabilistic hierarchical model for generation”. In Proceedings of the 18th International Conference on Computational Linguistics, Saarbrucken, Germany, 2000.
5 S. Varges. “Instance-based Natural Language Generation”. Ph.D. thesis, School of Informatics, University of Edinburgh, 2003.
6 A. Ratnaparkhi. “Trainable approaches to surface natural language generation and their application to conversational dialogue systems”. Computer, Speech & Language, 16(3):435– 455, 2002.
7 A. Oh and A. Rudnicky. “Stochastic natural language generation for spoken dialogue systems”. Computer Speech & Language, pp. 387–407, 2002.
8 J. Allen, D. Byron, M. Dzikovska, G. Ferguson, L. Galescu and A. Stent. “An architecture for a generic dialogue shell”. Natural Language Engineering, 6(3), 2000.
9 A. Belz. “Statistical generation: Three methods compared and evaluated”. In Proceedings of the 10th European Workshop on Natural Language Generation, ENLG 05, 2005.
10 A. Mustapha, M. N. Sulaiman, R. Mahmod and M. H. Selamat. “Classification-and-ranking architecture for response generation based on intentions”. International Journal of Computer Science and Network Security, 8(12):253–258, 2008.
11 M. White. “Reining in CCG chart realization”. In Proceedings of the 3rd International Natural Language Generation Conference, Hampshire, UK, 2004.
12 E. Velldal and S. Oepen. “Maximum entropy model for realization ranking”. In Proceedings of the 10th MT-Summit (X), Phuket, Thailand, 2005.
13 G.v.d. Hoeven, A. Andernach, S.v.d. Burgt, G-J. Kruijff, A. Nijholt, J. Schaake and F.d. Jong. “SCHISMA: A natural language accessible theater information and booking system”. In Proceedings of the 1st Internation Workshop on Applications of Natural Language to Data Bases, pp. 271-285, Versailles, France, 1995.
14 J. Hulstijn. “Dialogue models for inquiry and transaction”. Ph.D. thesis, University of Twente, Netherlands, 2000.
15 A. Stent. “A conversation acts model for generating spoken dialogue contributions”. Computer Speech and Language, 16(3):313–352, 2002.
Dr. Aida Mustapha
Assistant Professor MD. Nasir Sulaiman
Mr. Ramlan Mahmod
- Malaysia
Mr. Mohd. Hasan Selamat
- Malaysia