Loading...

Divided POMDP method for complex menu problems in spoken dialogue systems

Habibi, M ; Sharif University of Technology | 2010

428 Viewed
  1. Type of Document: Article
  2. DOI: 10.1109/SLT.2010.5700900
  3. Publisher: 2010
  4. Abstract:
  5. In this paper, a problem in spoken dialogue systems namely the menu problem, is introduced and solved by a POMDP model. To overcome the large size of the menu problem, a new method for achieving an optimal policy called divided POMDP method is introduced. Conditions for the problem to be solved by the proposed method are specified and the problem properties resulting in the given conditions are presented. The proposed method is evaluated using a typical menu problem with different menu sizes and it is shown that this method is superior to the conventional methods such as FRTDP for the problems it is capable to solve. Moreover, it converges faster in getting to an optimal policy
  6. Keywords:
  7. Conventional methods ; Dialogue management ; Large sizes ; Menu problem ; Optimal policies ; Partially observable Markov decision process ; Spoken dialogue system ; Decision making ; Markov processes ; Optimization ; Speech processing ; Speech recognition
  8. Source: 2010 IEEE Workshop on Spoken Language Technology, SLT 2010 - Proceedings, 12 December 2010 through 15 December 2010 ; 2010 , Pages 484-489 ; 9781424479030 (ISBN)
  9. URL: http://ieeexplore.ieee.org/document/5700900