Abstract
In this paper, we construct and evaluate a fully automated text-based cooperative persuasive dialogue system, which is able to persuade the user to take a specific action while maintaining user satisfaction. In our previous works, we created a dialogue management module for cooperative persuasive dialogue (Hiraoka et al., Reinforcement learning of cooperative persuasive dialogue policies using framing, Proceedings of international conference on computational linguistics (COLING), 2014), but only evaluated it in a wizard-of-Oz setting, as we did not have the capacity for natural language generation (NLG) and natural language understanding (NLU). In this work, the main technical contribution is the design of the NLU and the NLG modules which allows us to remove this bottleneck and create the first fully automatic cooperative persuasive dialogue system. Based on this system, we performed an evaluation with real users. Experimental results indicate that the learned policy is able to effectively persuade the users: the reward of the proposed model is much higher than baselines and almost the same as a dialogue manager controlled by a human. This tendency is almost the same as our previous evaluation using a wizard-of-Oz framework (Hiraoka et al., Reinforcement learning of cooperative persuasive dialogue policies using framing, Proceedings of international conference on computational linguistics (COLING), 2014), demonstrates that the proposed NLU and NLG modules are effective for cooperative persuasive dialogue.
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
Notes
- 1.
The salesperson is not told this information about customer preferences.
- 2.
Values of these variables are set at the beginning of dialogue and invariant over the dialogue.
- 3.
In this paper, we use “. ” for representing the membership relation between variables. For example, \(\mathrm{Var}1.\mathrm{Var}2\) means that Var2 is a member variable of Var1.
References
Breiman L (1996) Bagging predictors. Mach Learn 24(2):123–140
Georgila K (2013) Reinforcement learning of two-issue negotiation dialogue policies. In: Proceedings of the special interest group on discourse and dialogue (SIGDIAL)
Georgila K, Traum D (2011) Reinforcement learning of argumentation dialogue policies in negotiation. In: Proceedings of international speech (INTERSPEECH)
Heeman PA (2009) Representing the reinforcement learning state in a negotiation dialogue. In: Proceedings of IEEE automatic speech recognition and understanding workshop (ASRU)
Hiraoka T, Yamauchi Y, Neubig G, Sakti S, Toda T, Nakamura S (2013) Dialogue management for leading the conversation in persuasive dialogue systems. In: Proceedings of IEEE automatic speech recognition and understanding workshop (ASRU)
Hiraoka T, Neubig G, Sakti S, Toda T, Nakamura S (2014a) Construction and analysis of a persuasive dialogue corpus. In: Proceedings of the international workshop on spoken dialog systems (IWSDS)
Hiraoka T, Neubig G, Sakti S, Toda T, Nakamura S (2014b) Reinforcement learning of cooperative persuasive dialogue policies using framing. In: Proceedings of international conference on computational linguistics (COLING)
Irwin L, Schneider SL, Gaeth GJ (2013) All frames are not created equal: a typology and critical analysis of framing effects. Organ Behav Hum Decis Process 76(2):149–188
ISO24617-2: Language resource management-Semantic annotation frame work (SemAF). Part2: Dialogue acts. ISO (2010)
Kudo T, Yamamoto K, Matsumoto Y (2004) Applying conditional random fields to Japanese morphological analysis. In: Proceedings of conference on empirical methods in natural language processing (EMNLP), pp 707–710
Lee C, Jung S, Kim S, Lee GG (2009) Example-based dialog modeling for practical multi-domain dialog system. Speech Commun 51(5):466–484
Mark H, Eibe F, Geoffrey H, Bernhard P, Peter R, Ian HW (2009) The WEKA Data Mining Software: An Update; SIGKDD Explorations, 11(1)
Mazzotta I, de Rosis F (2006) Artifices for persuading to improve eating habits. In: AAAI spring symposium: argumentation for consumers of healthcare
Paruchuri P, Chakraborty N, Zivan R, Sycara K, Dudik M, Gordon G (2009) POMDP based negotiation modeling. In: Proceedings of the first MICON (modeling intercultural collaboration and negotiation), pp 66–78
Riedmiller M (2005) Neural fitted Q iteration - first experiences with a data efficient neural reinforcement learning method. In: Gama J, Camacho R, Brazdil PB, Jorge AM, Torgo L (eds) Machine learning: ECML. Springer, Berlin
Schaul T, Bayer J, Wierstra D, Sun Y, Felder M, Sehnke F, Ruckstiess T, Schmidhuber J (2010) Pybrain. J Mach Learn Res 11:743–746
Williams JD, Young S (2007) Partially observable Markov decision processes for spoken dialog systems. Comput Speech Lang 21(2):393–422
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2015 Springer International Publishing Switzerland
About this chapter
Cite this chapter
Hiraoka, T., Neubig, G., Sakti, S., Toda, T., Nakamura, S. (2015). Evaluation of a Fully Automatic Cooperative Persuasive Dialogue System. In: Lee, G., Kim, H., Jeong, M., Kim, JH. (eds) Natural Language Dialog Systems and Intelligent Assistants. Springer, Cham. https://doi.org/10.1007/978-3-319-19291-8_15
Download citation
DOI: https://doi.org/10.1007/978-3-319-19291-8_15
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-19290-1
Online ISBN: 978-3-319-19291-8
eBook Packages: Computer ScienceComputer Science (R0)