Loading...

Learning Dialogue Management in Spoken Dialogue Systems

Habibi, Maryam | 2010

507 Viewed
  1. Type of Document: M.Sc. Thesis
  2. Language: Farsi
  3. Document No: 40878 (19)
  4. University: Sharif University of Technology
  5. Department: Computer Engineering
  6. Advisor(s): Sameti, Hossein
  7. Abstract:
  8. Applying spoken dialogue systems (SDS's) is growing in the real life more rapidly because of the advances in the design and management of these systems. The traditional touch tone computer telephony systems are being substituted by the SDS's. In a typical SDS, the user speaks naturally to the system through a phone line and the system provides the required information or performs the required action. Banking and ticket reservation are typical examples of the prevalent SDS's. A spoken dialogue system has four units: automatic speech recognition (ASR), natural language understanding (NLU), dialogue management (DM), and spoken language generation (SLG). In this work, the first spoken dialogue system which is developed for the Persian language is introduced. This is a ticket reservation system with Persian ASR and NLU modules. The focus of the paper is on improving learning process of the dialogue management unit. In this work, real on-line training data are used during the learning process for the first time. For on-line learning, the effect of the variations of discount factor (γ) on the learning speed is investigated as the second contribution of the research. The optimal values for γ are found and the variation pattern of the action-value function (Q) in the learning process is obtained. A probabilistic policy for action selection is proposed instead of the conventional greedy policies as the 4th contribution of this work.

  9. Keywords:
  10. Reinforcement Learning ; Dialogue Management ; Spoken Dialoge System

 Digital Object List

 Bookmark

No TOC