A Proposal for the Development of Lifelong Dialog Systems

摘要

In this paper we describe a proposal that employs Soft Computing techniques for developing intelligent dialog systems that can improve over time. To do this, our proposal merges statistical dialog management methodologies, intentional and emotional information in order to make dialog managers more efficient and adaptive. The prediction of the user intention and emotion is carried out for each user turn in the dialog by means of specific modules that are conceived as an intermediate phase between natural language understanding and dialog management in the architecture of these systems. We have applied and evaluated our method in the UAH system, for which the evaluation results show that merging both sources of information improves system performance as well as its perceived quality.