Learning Optimal Dialogue Strategies: A Case Study of a Spoken Dialogue Agent for Email

By Marilyn A. Walker, Jeanne Fromer, Shrikanth S. Narayanan. 1998

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Citations in the corpus

Hybrid Reinforcement/Supervised Learning of Dialogue Policies from Fixed Data Sets (2008, methodology): “analysis reported in Walker et al. (2001) within the PARADISE evaluation framework (Walker, Kamm, and Litman 2000).”
Controlling User Perceptions of Linguistic Style: Trainable Generation of Personality Traits (2011, background): “…of a dialogue manager and a TTS component, in order to project a consistent personality to the user, or to use a reinforcement learning approach to train the dialogue manager (Walker, Fromer, and Narayanan 1998; Singh et al. 2002), with personality judgments as the objective function.”
Information state and dialogue management in the TRINDI dialogue move engine toolkit (2000, background): “While any well-designed system (e.g. Smith and Hipp 1994; Walker et al. 1998) should allow a range of experimentation of different parameters, it is much more difficult to compare different systems or approaches to the same phenomena.”
Automatic Learning and Evaluation of User-Centered Objective Functions for Dialogue System Optimisation (2008, methodology): “In particular, we construct a data-driven objective function using the PARADISE framework, and use it for automatic dialogue strategy optimisation following pioneering work by (Walker et al., 1998).”
POMDP-Based Statistical Spoken Dialog Systems: A Review (2013, background): “This work was quickly developed by others [45], [46], [48]–[51], [130], [140]–[151].”
Submission Category : Applications , Preference : ORAL Reinforcement Learning for Spoken Dialogue Systems (2007, unknown): “Previous work [6] h as largely dealt with these issues by imposing a priori limitations on the features used to repr esent approximate state, and then exploring just one of the potential reward measures.”
Spoken Dialogue Management Using Probabilistic Reasoning (2000, methodology): “For example, MDPs have been used successfully for such tasks as retrieving e-mail or making travel arrangements (Walker et al., 1998; Levin et al., 1998) over the phone, task domains that are generally low in both noise and ambiguity .”