MAS Architectural Model for Dialog Systems with Advancing Conversations

Authors

  • K. Mugoye  Department of Computer Science, Maseno University, Private Bag, Maseno, Kenya
  • Dr. H. Okoyo  Department of Computer Science, Maseno University, Private Bag, Maseno, Kenya
  • Dr. S. McOyowo  Department of Computer Science, Maseno University, Private Bag, Maseno, Kenya

DOI:

https://doi.org//10.32628/CSEIT183854

Keywords:

Dialog Manager, Dialog System, Task Oriented Dialog System, Artificial Intelligence, Conversation, Reinforcement Learning, Multi-agent System, Human-Agent.

Abstract

Recent handcrafts on dialog manager in task-oriented dialog systems (TODS) offer great promises on handling conversations. However, most tend to be shortsighted in handling advancing conversations. Modelling the future direction on conversations is crucial for TODS that can be scaled across multi-domain. This paper proposes a novel architectural model for the dialog manager, (MAS_DM). In this model, the dialog manager is a MAS. The architecture consists of multiple intelligent interacting agents, namely, state agent, master agent, and dialog agents. Each agent performs a set of tasks to achieve the overall goal of advancing the conversation within a topic. In this paper, the particular component of the Dialogue Manager, and Strategy selection has been discussed in detail. The notion of learning is essential, since it is intended to provide a means to which the agents will adapt to their environment. We show how to combine MAS and RL to enable agents learn a topic of interest and support an advancing conversation on the same. This will enable the realization of advancing conversations between a human and the TODS on a given topic.

References

  1. K. Mugoye, H. Okoyo and S. McOyowo, "Integrating Human Conversation Models Towards Improving Interaction In Text Based Dialog Systems," International Journal of Scientific Research in Computer Science, Engineering and Information Technology, vol. 3, no. 5, 2018.
  2. H. Trieu, H. Iida, N. Bao and L. Nguyen, "Towards Developing Dialogue Systems with Entertaining Conversations," 2017.
  3. M. Ghazvininejad, C. Brockett, M. Chang, B. Dolan, J. Gao, W. Yih and M. Galley, "A Knowledge-Grounded Neural Conversation Model," 2017.
  4. G. Weisz, P. Budzianowski, P. Su and M. Gasi, "Efficient deep reinforcement learning for dialogue systems with large action spaces," 2018.
  5. S. Singh, M. Kearns, D. Litman and M. Walker, "Reinforcement Learning for Spoken Dialogue Systems," 2000.
  6. J. Li, W. Monroe, A. Ritter, M. Galley, J. Gao and D. Jurafsky, "Deep Reinforcement Learning for Dialogue Generation," in Empirical Methods in Natural Language Processing, Austin, 2016.

IInternational Journal of Scientific Research in Computer Science, Engineering and Information Technology

Downloads

Published

2018-11-30

Issue

Volume 3, Issue 8, November-December-2018

Section

Research Articles

License

Copyright (c) IJSRCSEIT

Creative Commons License

This work is licensed under a Creative Commons Attribution 4.0 International License.

How to Cite

[1]
K. Mugoye, Dr. H. Okoyo, Dr. S. McOyowo, " MAS Architectural Model for Dialog Systems with Advancing Conversations , IInternational Journal of Scientific Research in Computer Science, Engineering and Information Technology(IJSRCSEIT), ISSN : 2456-3307, Volume 3, Issue 8, pp.247-252, November-December-2018. Available at doi : https://doi.org/10.32628/CSEIT183854