论文信息 - NJFun- A Reinforcement Learning Spoken Dialogue System

NJFun- A Reinforcement Learning Spoken Dialogue System

This paper describes NJFun, a real-time spoken dialogue system that provides users with information about things to do in New Jersey. NJFun automatically optimizes its dialogue strategy over time, by using a methodology for applying reinforcement learning to a working dialogue system with human users.

[1] Marilyn A. Walker,et al. Empirical Evaluation of a Reinforcement Learning Spoken Dialogue System , 2000, AAAI/IAAI.

[2] Marilyn A. Walker,et al. Automatic Optimization of Dialogue Management , 2000, COLING.

[3] Richard S. Sutton,et al. Introduction to Reinforcement Learning , 1998 .

[4] Morena Danieli,et al. Metrics for Evaluating Dialogue Strategies in a Spoken Language System , 1996, ArXiv.