Spoken dialogue management using probabilistic reasoning

Subscribe (Full Service)


	Search: The ACM Digital Library The Guide

	Feedback
Take a look at the new version of this page: [ beta version ]. Tell us what you think.

Spoken dialogue management using probabilistic reasoning

Full text

Publisher Site , Pdf

Pdf (146 KB)

Source

Annual Meeting of the ACL archive
Proceedings of the 38th Annual Meeting on Association for Computational Linguistics table of contents

Hong Kong

Pages: 93 - 100

Year of Publication: 2000

Authors

Nicholas Roy	Carnegie Mellon University, Pittsburgh, PA
Joelle Pineau	Carnegie Mellon University, Pittsburgh, PA
Sebastian Thrun	Carnegie Mellon University, Pittsburgh, PA

Publisher

Association for Computational Linguistics Morristown, NJ, USA

Bibliometrics

Downloads (6 Weeks): 3, Downloads (12 Months): 42, Citation Count: 28

Additional Information:

abstract references cited by collaborative colleagues

Tools and Actions:	Review this Article Save this Article to a Binder Display Formats: BibTeX EndNote ACM Ref

DOI Bookmark:	10.3115/1075218.1075231

ABSTRACT

Spoken dialogue managers have benefited from using stochastic planners such as Markov Decision Processes (MDPs). However, so far, MDPs do not handle well noisy and ambiguous speech utterances. We use a Partially Observable Markov Decision Process (POMDP)-style approach to generate dialogue strategies by inverting the notion of dialogue state; the state represents the user's intentions, rather than the system state. We demonstrate that under the same noisy conditions, a POMDP dialogue manager makes fewer mistakes than an MDP dialogue manager. Furthermore, as the quality of speech recognition degrades, the POMDP dialogue manager automatically adjusts the policy.

REFERENCES

Note: OCR errors may be found in this Reference List extracted from the full text article. ACM has opted to expose the complete List rather than only correct and linked references.

	1	Harald Aust and Hermann Ney. 1998. Evaluating dialog systems used in the real world. In Proc. IEEE ICASSP, volume 2, pages 1053--1056.
	2	A. Black, P. Taylor, and R. Caley, 1999. The Festival Speech Synthesis System, 1.4 edition.
	3	Anthony Cassandra, Michael L. Littman, and Nevin L. Zhang. 1997. Incremental pruning: A simple, fast, exact algorithm for partially observable Markov decision processes. In Proc. 13th Ann. Conf. on Uncertainty in Artificial Intelligence (UAI-97), pages 54--61, San Francisco, CA.
	4	Leslie Pack Kaelbling , Michael L. Littman , Anthony R. Cassandra, Planning and acting in partially observable stochastic domains, Artificial Intelligence, v.101 n.1-2, p.99-134, May 1998 [doi>10.1016/S0004-3702(98)00023-X]
	5	Esther Levin, Roberto Pieraccini, and Wieland Eckert. 1998. Using Markov decision process for learning dialogue strategies. In Proc. International Conference on Acoustics, Speech and Signal Processing (ICASSP).
	6	George E. Monahan. 1982. A survey of partially observable Markov decision processes. Management Science, 28(1):1--16.
	7	Yasuhisa Niimi and Yutaka Kobayashi. 1996. Dialog control strategy based on the reliability of speech recognition. In Proc. International Conference on Spoken Language Processing (ICSLP).
	8	Ronald Parr and Stuart Russell. 1995. Approximating optimal policies for partially observable stochastic domains. In Proceedings of the 14th International Joint Conferences on Artificial Intelligence.
	9	M. Ravishankar. 1996. Efficient Algorithms for Speech Recognition. Ph.D. thesis, Carnegie Mellon.
	10	Nicholas Roy and Sebastian Thrun. 1999. Coastal navigation with mobile robots. In Advances in Neural Processing Systems, volume 12.
	11	Satinder Singh, Michael Kearns, Diane Litman, and Marilyn Walker. 1999. Reinforcement learning for spoken dialog systems. In Advances in Neural Processing Systems, volume 12.
	12	E. Sondik. 1971. The Optimal Control of Partially Observable Markov Decision Processes. Ph.D. thesis, Stanford University, Stanford, California.
	13	Sebastian Thrun. 1999. Monte carlo pomdps. In S. A. Solla, T. K. Leen, and K. R. Müller, editors, Advances in Neural Processing Systems, volume 12.
	14	Marilyn A. Walker , Jeanne C. Fromer , Shrikanth Narayanan, Learning optimal dialogue strategies: a case study of a spoken dialogue agent for email, Proceedings of the 17th international conference on Computational linguistics, p.1345-1351, August 10-14, 1998, Montreal, Quebec, Canada
	15	Sheryl R. Young, Use of dialogue, pragmatics and semantics to enhance speech recognition, Speech Communication, v.9 n.5-6, p.551-564, Dec. 1990 [doi>10.1016/0167-6393(90)90030-D]

CITED BY 28

	Thorsten Bohnenberger, Decision-theoretic planning for intelligent user interfaces, Eighteenth national conference on Artificial intelligence, p.978-978, July 28-August 01, 2002, Edmonton, Alberta, Canada
	Matthew Rudary , Satinder Singh , Martha E. Pollack, Adaptive cognitive orthotics: combining reinforcement learning and constraint-based temporal reasoning, Proceedings of the twenty-first international conference on Machine learning, p.91, July 04-08, 2004, Banff, Alberta, Canada
	Renaud Lecœuche, Learning optimal dialogue management rules by using reinforcement learning and inductive logic programming, Second meeting of the North American Chapter of the Association for Computational Linguistics on Language technologies 2001, p.1-7, June 01-07, 2001, Pittsburgh, Pennsylvania
	Katrin Kirchhoff , Mari Ostendorf, Directions for multi-party human-computer interaction research, Proceedings of the HLT-NAACL 2003 workshop on Research directions in dialogue processing, p.7-9, May 31, 2003, Edmonton, Alberta, Canada
	Tim Paek , Roberto Pieraccini, Automating spoken dialogue management design using machine learning: An industry perspective, Speech Communication, v.50 n.8-9, p.716-729, August, 2008
	Johannes Pittermann , Angela Pittermann, A data-oriented approach to integrate emotions in adaptive dialogue management, Proceedings of the 12th international conference on Intelligent user interfaces, January 28-31, 2007, Honolulu, Hawaii, USA
	Finale Doshi , Nicholas Roy, Efficient model learning for dialog management, Proceeding of the ACM/IEEE international conference on Human-robot interaction, March 10-12, 2007, Arlington, Virginia, USA
	Josep M. Porta , Nikos Vlassis , Matthijs T.J. Spaan , Pascal Poupart, Point-Based Value Iteration for Continuous POMDPs, The Journal of Machine Learning Research, 7, p.2329-2367, 12/1/2006
	Maria Wolters , Kallirroi Georgila , Johanna D. Moore , Robert H. Logie , Sarah E. MacPherson , Matthew Watson, Reducing working memory load in spoken dialogue systems, Interacting with Computers, v.21 n.4, p.276-287, August, 2009
	David Griol , Lluís F. Hurtado , Encarna Segarra , Emilio Sanchis, A statistical approach to spoken dialog systems design and evaluation, Speech Communication, v.50 n.8-9, p.666-682, August, 2008
	Finale Doshi , Nicholas Roy, The permutable POMDP: fast solutions to POMDPs for preference elicitation, Proceedings of the 7th international joint conference on Autonomous agents and multiagent systems, May 12-16, 2008, Estoril, Portugal
	Konrad Scheffler , Steve Young, Automatic learning of dialogue strategy using dialogue simulation and reinforcement learning, Proceedings of the second international conference on Human Language Technology Research, March 24-27, 2002, San Diego, California
	Finale Doshi , Nicholas Roy, Spoken language interaction with model uncertainty: an adaptive human-robot interaction system, Connection Science, v.20 n.4, p.299-318, December 2008
	James Henderson , Oliver Lemon , Kallirroi Georgila, Hybrid reinforcement/supervised learning of dialogue policies from fixed data sets, Computational Linguistics, v.34 n.4, p.487-511, December 2008
	Joel R. Tetreault , Diane J. Litman, A Reinforcement Learning approach to evaluating state representations in spoken dialogue systems, Speech Communication, v.50 n.8-9, p.683-696, August, 2008
	Sebastian Thrun, Toward a framework for human-robot interaction, Human-Computer Interaction, v.19 n.1, p.9-24, June 2004
	Jason D. Williams, Evaluating user simulations with the Cramér-von Mises divergence, Speech Communication, v.50 n.10, p.829-846, October, 2008
	Finale Doshi , Joelle Pineau , Nicholas Roy, Reinforcement learning with limited reinforcement: using Bayes risk for active learning in POMDPs, Proceedings of the 25th international conference on Machine learning, p.256-263, July 05-09, 2008, Helsinki, Finland
	Trung h. Bui , Mannes Poel , Anton Nijholt , Job Zwiers, A tractable hybrid ddn–pomdp approach to affective dialogue modeling for probabilistic frame-based dialogue systems, Natural Language Engineering, v.15 n.2, p.273-307, April 2009
	Amin Atrash , Joelle Pineau, A bayesian reinforcement learning approach for customizing human-robot interfaces, Proceedings of the 13th international conference on Intelligent user interfaces, February 08-11, 2009, Sanibel Island, Florida, USA
	Jason D. Williams , Steve Young, Partially observable Markov decision processes for spoken dialog systems, Computer Speech and Language, v.21 n.2, p.393-422, April, 2007
	Steve Young , Milica Gašić , Simon Keizer , François Mairesse , Jost Schatzmann , Blaise Thomson , Kai Yu, The Hidden Information State model: A practical framework for POMDP-based spoken dialogue management, Computer Speech and Language, v.24 n.2, p.150-174, April, 2010
	Maria Wolters , Kallirroi Georgila , Johanna D. Moore , Sarah E. MacPherson, Being Old Doesn’t Mean Acting Old: How Older Users Interact with Spoken Dialog Systems, ACM Transactions on Accessible Computing (TACCESS), v.2 n.1, p.1-39, May 2009
	Heriberto Cuayáhuitl , Steve Renals , Oliver Lemon , Hiroshi Shimodaira, Evaluation of a hierarchical reinforcement learning spoken dialogue system, Computer Speech and Language, v.24 n.2, p.395-429, April, 2010
	Jesse Hoey , Pascal Poupart, Solving POMDPs with continuous or large discrete observation spaces, Proceedings of the 19th international joint conference on Artificial intelligence, p.1332-1338, July 30-August 05, 2005, Edinburgh, Scotland
	Teruhisa Misu , Tatsuya Kawahara, Bayes risk-based dialogue management for document retrieval system with speech interface, Speech Communication, v.52 n.1, p.61-71, January, 2010
	Beth Ann Hockey , Manny Rayner, Using paraphrases of deep semantic representions to support regression testing in spoken dialogue systems, Proceedings of the Workshop on Software Engineering, Testing, and Quality Assurance for Natural Language Processing, p.14-21, June 05-05, 2009, Boulder, Colorado
	M. Gašić , S. Keizer , F. Mairesse , J. Schatzmann , B. Thomson , K. Yu , S. Young, Training and evaluation of the HIS POMDP dialogue system in noise, Proceedings of the 9th SIGdial Workshop on Discourse and Dialogue, June 19-20, 2008, Columbus, Ohio

Collaborative Colleagues:

Nicholas Roy: colleagues

Joelle Pineau: colleagues

Sebastian Thrun: colleagues

Adobe Acrobat

QuickTime

Windows Media Player

Real Player