Which Is the Most Appropriate Response? Combining Decision-Support Systems and Conversational Interfaces

In this paper we propose combining decision support systems with spoken dialog systems to facilitate training call-center human operators. In our proposal, the system responses are learned automatically from a dialog corpus by means of a statistical approach based on evolving classifiers. This permits inferring knowledge automatically, that is, the system may infer decisions in complex settings where it is not easy to establish clear hand-crafted rules. Also, the training corpus can be provided from human-human recordings so that the experience of highly qualified human operators can be distilled into the system and offered implicitly to the operators being trained with it. Our proposal has been evaluated with a practical spoken dialog system providing railway information, which follows our proposed approach to integrate a decision support system for the selection of the next system action.