Abstract
Partially Observable Markov Decision Process (POMDP) has been widely used as dialogue management in slot-filling Spoken Dialogue System (SDS). But there are still lots of open problems. The contribution of this paper lies in two aspects. Firstly, the observation probability of POMDP is estimated from the N-Best list of Automatic Speech Recognition (ASR) rather than the top one. This modification gives SDS a chance to address the uncertainty of ASR. Secondly, a dynamic binding technique is proposed for slots with infinite values so as to deal with uncertainty of talking object. The proposed methods have been implemented on a teach-and-learn spoken dialogue system. Experimental results show that performance of system improves significantly by introducing the proposed methods.
This is a preview of subscription content, log in via an institution to check access.
References
Barto, A.G.: Reinforcement Learning: An Introduction. MIT press, Cambridge (1998)
Hastie, H., Aufaure, M.a., Alexopoulos, P., Cuayáhuitl, H., Dethlefs, N., Gasic, M., Henderson, J., Lemon, O., Liu, X., Mika, P., Mustapha, N.B., Rieser, V., Thomson, B., Tsiakoulis, P., Vanrompay, Y., Villazon-terrazas, B., Young, S.: Demonstration of the Parlance system: a data-driven, incremental, spoken dialogue system for interactive search. In: Proceedings of the SIGDIAL 2013 Conference, pp. 154–156 (2013). http://www.aclweb.org/anthology/W/W13/W13-4026
Jokinen, K., McTear, M.: Spoken dialogue systems. Synth. Lect. Hum. Lang. Technol. 2(1), 1–151 (2009)
Kaelbling, L.P., Littman, M.L., Cassandra, A.R.: Planning and acting in partially observable stochastic domains. Artif. Intell. 101(1), 99–134 (1998)
Kurniawati, H., Hsu, D., Lee, W.S.: SARSOP: efficient point-based POMDP planning by approximating optimally reachable belief spaces. In: Robotics: Science and Systems (2008)
Levin, E., Pieraccini, R., Eckert, W.: A stochastic model of human-machine interaction for learning dialog strategies. IEEE Trans. Speech Audio Process. 8(1), 11–23 (2000)
McTear, M.: Spoken dialogue technology: enabling the conversational user interface. ACM Comput. Surv. (CSUR) 34(1), 90–169 (2002)
Seneff, S., Polifroni, J.: Dialogue management in the Mercury flight reservation system. In: Proceedings of the 2000 ANLP/NAACL Workshop on Conversational Systems, vol. 3. pp. 11–16. Association for Computational Linguistics (2000)
Shani, G., Pineau, J., Kaplow, R.: A survey of point-based POMDP solvers. Auton. Agent. Multi-Agent Syst. 27(1), 1–51 (2012). http://link.springer.com/10.1007/s10458-012-9200-2
Williams, J.D.: A case study of applying decision theory in the real world: POMDPs and spoken dialog systems. In: Decision Theory Models for Applications in Artificial Intelligence: Concepts and Solutions, pp. 315–342 (2010)
Williams, J.D., Young, S.: Partially observable Markov decision processes for spoken dialog systems. Comput. Speech Lang. 21(2), 393–422 (2007)
Young, S., Gasic, M., Thomson, B., Williams, J.D.: Pomdp-based statistical spoken dialog systems: A review. Proc. IEEE 101(5), 1160–1179 (2013)
Young, S., Gašić, M., Keizer, S., Mairesse, F., Schatzmann, J., Thomson, B., Yu, K.: The hidden information state model: A practical framework for POMDP-based spoken dialogue management. Comput. Speech Lang. 24(2), 150–174 (2010). http://linkinghub.elsevier.com/retrieve/pii/S0885230809000230
Zue, V., Seneff, S., Glass, J.R., Polifroni, J., Pao, C., Hazen, T.J., Hetherington, L.: JUPITER: A telephone-based conversational interface for weather information. IEEE Trans. Speech Audio Process. 8(1), 85–96 (2000)
Acknowledgments
This work was partially supported by National Natural Science Foundation of China (No.61273365, No.61202248), discipline building plan in 111 base (No.B08004) and Engineering Research Center of Information Networks, Ministry of Education.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 2.5 International License (http://creativecommons.org/licenses/by-nc/2.5/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.
The images or other third party material in this chapter are included in the chapter's Creative Commons license, unless indicated otherwise in a credit line to the material. If material is not included in the chapter's Creative Commons license and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder.
Copyright information
© 2015 Springer International Publishing Switzerland
About this paper
Cite this paper
Wu, G., Yuan, C., Leng, B., Wang, X. (2015). Finite-to-Infinite N-Best POMDP for Spoken Dialogue Management. In: Sun, M., Liu, Z., Zhang, M., Liu, Y. (eds) Chinese Computational Linguistics and Natural Language Processing Based on Naturally Annotated Big Data. CCL NLP-NABD 2015 2015. Lecture Notes in Computer Science(), vol 9427. Springer, Cham. https://doi.org/10.1007/978-3-319-25816-4_30
Download citation
DOI: https://doi.org/10.1007/978-3-319-25816-4_30
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-25815-7
Online ISBN: 978-3-319-25816-4
eBook Packages: Computer ScienceComputer Science (R0)