Naren Ramakrishnan
Robert G. Capra
Manuel A. Pérez-Quiñones
ABSTRACT
We show that partial evaluation can be usefully viewed as a programming model for realizing mixed-initiative functionality in interactive applications. Mixed-initiative interaction between two participants is one where the parties can take turns at any time to change and steer the flow of interaction. We concentrate on the facet of mixed-initiative referred to as 'unsolicited reporting' and demonstrate how out-of-turn interactions by users can be modeled by 'jumping ahead' to nested dialogs (via partial evaluation). Our approach permits the view of dialog management systems in terms of their support for staging and simplifying inter-actions; we characterize three different voice-based interaction technologies using this viewpoint. In particular, we show that the built-in form interpretation algorithm (FIA) in the VoiceXML dialog management architecture is actually a (well disguised) combination of an interpreter and a partial evaluator.
- 1.J. Allen. Natural Language Understanding. Benjamin Cummings, 1995. Second Edition. Google Scholar
Digital Library
- 2.J. Allen, D. Byron, M. Dzikovska, G. Ferguson, L. Galescu, and A. Stent. Towards Conversational Human-Computer Interaction. AI Magazine, 2001. to appear. Google ScholarDigital Library
- 3.J. Allen, C. Guinn, and E. Horvitz. Mixed-Initiative Interaction. IEEE Intelligent Systems, Vol. 14(5):pages 14-23, Sep-Oct 1999. Google ScholarDigital Library
- 4.L. Boyer, P. Danielsen, J. Ferrans, G. Karam, D. Ladd, B. Lucas, and K. Rehor. Voice eXtensible Markup Language: VoiceXML. Technical report, VoiceXML Forum, May 2000. Version 1.00.Google Scholar
- 5.H. Brunner, G. Whittemore, K. Ferrara, and J. Hsu. An Assessment of Written/Interaction Dialogue for Information Retrieval Applications. Human-Computer Interaction, Vol. 7:pages 197-249, 1992.Google ScholarDigital Library
- 6.M. Coulthard. An Introduction to Discourse Analysis. Longman, London, 1977.Google Scholar
- 7.E. Goffman. Replies and Responses. Language in Society, Vol. 5:pages 257-313, 1976.Google ScholarCross Ref
- 8.S. Haller and S. McRoy. Computational Models for Mixed Initiative Interaction (Papers from the 1997 AAAI Spring Symposium). Technical Report SS-97-04, AAAI/MIT Press, 1997.Google Scholar
- 9.N. Jones, C. Gomard, and P. Sestoft. Partial Evaluation and Automatic Program Generation. Prentice Hall International, 1993. Google ScholarDigital Library
- 10.D. Jurafsky and J. Martin. Speech and Language Processing: An Introduction to Natural Language Processing, Computational Linguistics, and Speech Recognition. Prentice Hall, 2000. Google ScholarDigital Library
- 11.S. Levinson. Pragmatics. Cambridge University Press, 1983. Cambridge Textbooks in Linguistics.Google Scholar
- 12.S. McGlashan, D. Burnett, P. Danielsen, J. Ferrans, A. Hunt, G. Karam, D. Ladd, B. Lucas, B. Porter, K. Rehor, and S. Tryphonas. Voice eXtensible Markup Language: VoiceXML. Technical report, VoiceXML Forum, October 2001. Version 2.00.Google Scholar
- 13.D. Novick and S. Sutton. What is Mixed-Initiative Interaction? In S. Haller and S. McRoy, editors, Procedings of the AAAI Spring Symposium on Computational Models for Mixed Initiative Interaction, pages 114-116. AAAI/MIT Press, 1997.Google Scholar
- 14.Perez-Quinones, M.A. and Sibert, J.L. A Collaborative Model of Feedback in Human-Computer Interaction. In Proceedings of the ACM Conference on Human Factors in Computing Systems (CHI'96), pages 316-323. Vancouver, BC, Canada, 1996. Google ScholarDigital Library
- 15.N. Ramakrishnan and S. Perugini. The Partial Evaluation Approach to Information Personalization. ACM Transactions on Information Systems, August 2001. Communicated for publication. Also available as Technical Report cs.IR/0108003, Computing Research Repository (CoRR) at http://xxx.lanl.gov/abs/ cs.IR/0108003.Google Scholar
- 16.F. van Harmelen and A. Bundy. Explanation-Based Generalisation = Partial Evaluation. Artificial Intelligence, Vol. 36(3):pages 401-412, 1988. Google ScholarDigital Library
- 17.M. Veloso, J. Carbonell, A. P~rez, D. Borrajo, E. Fink, and J. Blythe. Integrating Planning and Learning: The PRODIGY Architecture. Journal of Experimental and Theoretical Artificial Intelligence, Vol. 7(1):pages 81-120, 1995.Google ScholarCross Ref
Index Terms
- Mixed-initiative interaction = mixed computation
Recommendations
Mixed-initiative interaction = mixed computation
We show that partial evaluation can be usefully viewed as a programming model for realizing mixed-initiative functionality in interactive applications. Mixed-initiative interaction between two participants is one where the parties can take turns at any ...
Natural Language, Mixed-initiative Personal Assistant Agents
IMCOM '18: Proceedings of the 12th International Conference on Ubiquitous Information Management and CommunicationThe increasing popularity and use of personal voice assistant technologies, such as Siri and Google Now, is driving and expanding progress toward the long-term and lofty goal of using artificial intelligence to build human-computer dialog systems ...
A language-based model for specifying and staging mixed-initiative dialogs
EICS '16: Proceedings of the 8th ACM SIGCHI Symposium on Engineering Interactive Computing SystemsSpecifying and implementing flexible human-computer dialogs, such as those used in kiosks, is complex because of the numerous and varied directions in which each user might steer a dialog. The objective of this research is to improve dialog ...
Comments