Abstract
Online learning of dialogue managers is a desirable but often costly property to obtain. Probabilistic Finite State Bi-Automata (PFSBA) have shown to provide a flexible and adaptive framework to achieve this goal. In this paper, an Attributed PFSBA (A-PSFBA) is implemented and experimentally compared with previous non-attributed PFSBA proposals. Then, a simple yet effective online learning algorithm that adapts the probabilistic structure of the Bi-Automata on the run is presented and evaluated. To this end, the User Model is also represented by an A-PFSBA and the impact of different user behaviors is tested. The proposed approaches are evaluated on the Let’s Go corpus, showing significant improvements on the dialogue success rates reported in previous works.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Gorin, A.L., Riccardi, G., Wright, J.H.: How may i help you? Speech Commun. 23(1–2), 113–127 (1997)
Bohus, D., Rudnicky, A.I.: The RavenClaw dialog management framework: architecture and systems. Comput. Speech Lang. 23, 332–361 (2009)
Thomson, B., Yu, K., Keizer, S., Gasic, M., Jurcicek, F., Mairesse, F., Young, S.: Bayesian dialogue system for the let’s go spoken dialogue challenge. In: Spoken Language Technology Workshop (SLT), pp. 460–465. IEEE (2010)
Hurtado, L.F., Planells, J., Segarra, E., Sanchis, E., Griol, D.: A stochastic finite-state transducer approach to spoken dialog management. In: INTERSPEECH, pp. 3002–3005 (2010)
Vinyals, O., Le, Q.: A Neural Conversational Model. abs/1506.05869 CoRR (2015)
Orozko, O.R., Torres, M.I.: Online learning of stochastic bi-automaton to model dialogues. In: Paredes, R., Cardoso, J.S., Pardo, X.M. (eds.) IbPRIA 2015. LNCS, vol. 9117, pp. 441–451. Springer, Cham (2015). doi:10.1007/978-3-319-19390-8_50
Raux, A., Langner, B., Bohus, D., Black, A.W., Eskenazi, M.: Let’s go public! Taking a spoken dialog system to the real world. In: Proceedings of Interspeech (2005)
Young, S., Gasic, M., Thomson, B., Williams, D.J.: POMDP-based statistical spoken dialog systems: a review. Proc. IEEE 101(5), 1160–1179 (2013)
Jurcıcek, F., Thomson, B., Young, S.: Reinforcement learning for parameter estimation in statistical spoken dialogue systems. Comput. Speech Lang. 26(3), 168–192 (2012)
Torres, M.I.: Stochastic bi-languages to model dialogs. In: Finite State Methods and Natural Language Processing, p. 9 (2013)
Torres, M.I., Benedí, J.M., Justo, R., Ghigi, F.: Modeling spoken dialog systems under the interactive pattern recognition framework. In: Gimel’farb, G., et al. (eds.) SSPR&SPR 2012. LNCS, vol. 7626, pp. 519–528. Springer, Heidelberg (2012)
Torres, M.I., Casacuberta, F.: Stochastic k-TSS bi-languages for machine transla tion. In: Proceedings of the 9th International Workshop on Finite State Models for Natural Language Processing (FSMNLP), pp. 98–106. Association for Computational Linguistics, Blois (2011)
Toselli, A.H., Vidal, E., Casacuberta, F. (eds.): Multimodal Interactive Pattern Recognition and Applications. Springer, Heidelberg (2011)
Ward, W., Issar, S.: The CMU ATIS system. In: Proceedings of ARPA Workshop on Spoken Language Technology, pp. 249–251 (1995)
Sutton, R. S., Barto, A. G.: Reinforcement Learning: An Introduction, vol. 1, No. 1. MIT press, Cambridge (1998)
Schatzmann, J., Young, S.: The hidden agenda user simulation model. IEEE Trans. Audio Speech Lang. Process. 17(4), 733–747 (2009)
Schatzmann, J., Georgila, K., Young, S.: Quantitative evaluation of user simulation techniques for spoken dialogue systems. In: Proceedings of 6th SIGDIAL, pp. 45–54 (2005)
Williams, J.D., Zweig, G.: End-to-end LSTM-based dialog control optimized with supervised and reinforcement learning. CoRR abs/1606.01269 (2016)
Zhao, T., Eskenazi, M.: Towards end-to-end learning for dialog state tracking and management using deep reinforcement learning. In: Proceedings of 17th Annual Meeting of the Special Interest Group on Discourse and Dialogue, pp. 1–10 (2016)
Serban, I.V., et al.: Building end-to-end dialogue systems using generative hierarchical neural network. In: Proceedings of 30th conference of AAAI (2016)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2017 Springer International Publishing AG
About this paper
Cite this paper
Serras, M., Torres, M.I., Del Pozo, A. (2017). Online Learning of Attributed Bi-Automata for Dialogue Management in Spoken Dialogue Systems. In: Alexandre, L., Salvador Sánchez, J., Rodrigues, J. (eds) Pattern Recognition and Image Analysis. IbPRIA 2017. Lecture Notes in Computer Science(), vol 10255. Springer, Cham. https://doi.org/10.1007/978-3-319-58838-4_3
Download citation
DOI: https://doi.org/10.1007/978-3-319-58838-4_3
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-58837-7
Online ISBN: 978-3-319-58838-4
eBook Packages: Computer ScienceComputer Science (R0)