Abstract
This paper proposes a novel Markov Decision Process (MDP) to solve the problem of learning an optimal strategy by a Dialogue Manager for a flight enquiry system. A unique representation of state is presented followed by a relevant action set and a reward model which is specific to different time-steps. Different Reinforcement Learning (RL) algorithms based on classical methods and Deep Learning techniques have been implemented for the execution of the Dialogue Management component. To establish the robustness of the system, existing Slot-Filling (SF) module has been integrated with the system. The system can still generate valid responses to act sensibly even if the SF module falters. The experimental results indicate that the proposed MDP and the system hold promise to be scalable across satisfying the intent of the user.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
Ran on Intel(R) Xeon(R) CPU E5-2650 v4 @ 2.20 GHz, 251 GB RAM.
References
Allen, J.F., Byron, D.K., Dzikovska, M., Ferguson, G., Galescu, L., Stent, A.: Toward conversational human-computer interaction. AI Magaz. 22(4), 27 (2001)
Arulkumaran, K., Deisenroth, M.P., Brundage, M., Bharath, A.A.: A brief survey of deep reinforcement learning. arXiv preprint arXiv:1708.05866 (2017)
Bohus, D., Rudnicky, A.I.: Error handling in the ravenclaw dialog management framework. In: Proceedings of the Conference on Human Language Technology and Empirical Methods in Natural Language Processing, pp. 225–232. Association for Computational Linguistics (2005)
Cuayáhuitl, H.: SimpleDS: a simple deep reinforcement learning dialogue system. In: Jokinen, K., Wilcock, G. (eds.) Dialogues with Social Robots. LNEE, vol. 999, pp. 109–118. Springer, Singapore (2017). https://doi.org/10.1007/978-981-10-2585-3_8
Cuayáhuitl, H., Yu, S., et al.: Deep reinforcement learning of dialogue policies with less weight updates (2017)
Fraser, N.: Assessment of interactive systems. In: Handbook of Standards and Resources for Spoken Language Systems, pp. 564–615. Mouton de Gruyter (1998)
Kaelbling, L.P., Littman, M.L., Moore, A.W.: Reinforcement learning: a survey. J. Artif. Intell. Res. 4, 237–285 (1996)
Levin, E., Pieraccini, R., Eckert, W.: Using markov decision process for learning dialogue strategies. In: Proceedings of the 1998 IEEE International Conference on Acoustics, Speech and Signal Processing, vol. 1, pp. 201–204. IEEE (1998)
Litman, D.J., Kearns, M.S., Singh, S., Walker, M.A.: Automatic optimization of dialogue management. In: Proceedings of the 18th Conference on Computational Linguistics, vol. 1, pp. 502–508. Association for Computational Linguistics (2000)
McTear, M.F.: Modelling spoken dialogues with state transition diagrams: experiences with the CSLU toolkit. In: Fifth International Conference on Spoken Language Processing (1998)
McTear, M.F.: Spoken dialogue technology: enabling the conversational user interface. ACM Comput. Surv. (CSUR) 34(1), 90–169 (2002)
Mesnil, G., He, X., Deng, L., Bengio, Y.: Investigation of recurrent-neural-network architectures and learning methods for spoken language understanding. In: Interspeech, pp. 3771–3775 (2013)
Mnih, V., et al.: Playing atari with deep reinforcement learning. arXiv preprint arXiv:1312.5602 (2013)
Price, P.J.: Evaluation of spoken language systems: the atis domain. In: Speech and Natural Language: Proceedings of a Workshop Held at Hidden Valley, Pennsylvania, 24–27 June 1990
Rieser, V., Lemon, O.: Reinforcement learning. In: Reinforcement Learning for Adaptive Dialogue Systems, pp. 29–52. Springer, Heidelberg (2011). https://doi.org/10.1007/978-3-642-24942-6
Schaul, T., Quan, J., Antonoglou, I., Silver, D.: Prioritized experience replay. arXiv preprint arXiv:1511.05952 (2015)
Singh, S.P., Kearns, M.J., Litman, D.J., Walker, M.A.: Reinforcement learning for spoken dialogue systems. In: Advances in Neural Information Processing Systems, pp. 956–962 (2000)
Sutton, R.S., Barto, A.G.: Reinforcement Learning: An Introduction, vol. 1. MIT press, Cambridge (1998)
Traum, D.: Approaches to dialogue systems and dialogue management. Lecture Notes, University of Southern California (2008). http://people.ict.usc.edu/~traum/ESSLLI08
Van Hasselt, H., Guez, A., Silver, D.: Deep reinforcement learning with double q-learning. In: AAAI, vol. 16, pp. 2094–2100 (2016)
Walker, M.A.: An application of reinforcement learning to dialogue strategy selection in a spoken dialogue system for email. J. Artif. Intell. Res. 12, 387–416 (2000)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2018 Springer Nature Switzerland AG
About this paper
Cite this paper
Saha, T., Gupta, D., Saha, S., Bhattacharyya, P. (2018). Reinforcement Learning Based Dialogue Management Strategy. In: Cheng, L., Leung, A., Ozawa, S. (eds) Neural Information Processing. ICONIP 2018. Lecture Notes in Computer Science(), vol 11303. Springer, Cham. https://doi.org/10.1007/978-3-030-04182-3_32
Download citation
DOI: https://doi.org/10.1007/978-3-030-04182-3_32
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-04181-6
Online ISBN: 978-3-030-04182-3
eBook Packages: Computer ScienceComputer Science (R0)