Proceedings of the KSPS conference (대한음성학회:학술대회논문집)

The Korean Society Of Phonetic Sciences And Speech Technology (대한음성학회)
권호 표지

Design of Markov Decision Process Based Dialogue Manager

마르코프 의사결정 과정에 기반한 대화 관리자 설계

  • Choi, Joon-Ki (Human Centric Interface Research Department Advanced Technology Laboratory, KT) ;
  • Eun, Ji-Hyun (Human Centric Interface Research Department Advanced Technology Laboratory, KT) ;
  • Chang, Du-Seong (Human Centric Interface Research Department Advanced Technology Laboratory, KT) ;
  • Kim, Hyun-Jeong (Human Centric Interface Research Department Advanced Technology Laboratory, KT) ;
  • Koo, Myong-Wan (Human Centric Interface Research Department Advanced Technology Laboratory, KT)
  • 최준기 (KT 미래기술연구소 HCI 연구 담당) ;
  • 은지현 (KT 미래기술연구소 HCI 연구 담당) ;
  • 장두성 (KT 미래기술연구소 HCI 연구 담당) ;
  • 김현정 (KT 미래기술연구소 HCI 연구 담당) ;
  • 구명완 (KT 미래기술연구소 HCI 연구 담당)
  • Published : 2006.11.17
Download PDF
⟨ Previous Next ⟩

Abstract

The role of dialogue manager is to select proper actions based on observed environment and inferred user intention. This paper presents stochastic model for dialogue manager based on Markov decision process. To build a mixed initiative dialogue manager, we used accumulated user utterance, previous act of dialogue manager, and domain dependent knowledge as the input to the MDP. We also used dialogue corpus to train the automatically optimized policy of MDP with reinforcement learning algorithm. The states which have unique and intuitive actions were removed from the design of MDP by using the domain knowledge. The design of dialogue manager included the usage of natural language understanding and response generator to build short message based remote control of home networked appliances.

Keywords