Modeling Spoken Decision Making Dialogue and Optimization of its Dialogue Strategy

This paper presents a spoken dialogue framework that helps users in making decisions. Users often do not have a definite goal or criteria for selecting from a list of alternatives. Thus the system has to bridge this knowledge gap and also provide the users with an appropriate alternative together with the reason for this recommendation through dialogue. We present a dialogue state model for such decision making dialogue. To evaluate this model, we implement a trial sightseeing guidance system and collect dialogue data. Then, we optimize the dialogue strategy based on the state model through reinforcement learning with a natural policy gradient approach using a user simulator trained on the collected dialogue corpus.