Can We Talk? Prospects for Automatically Training Spoken Dialogue Systems

There is a strong relationship between evaluation and methods for automatically training language processing systems, where generally the same resource and metrics are used both to train system components and to evaluate them. To date, in dialogue systems research, this general methodology is not typically applied to the dialogue manager and spoken language generator. I will argue that any metric that can be used to evaluate system performance should also be usable as a feedback function for automatically training the system. My argument is motivated with examples of the application of reinforcement learning to dialogue manager optimization, and the use of boosting to train the spoken language generator.