A Neural Network Approach to Intention Modeling forUser-Adapted Conversational Agents

Abstract

Spoken dialogue systems have been proposed to enable a more natural and intuitive interaction with the environment andhuman-computer interfaces. In this contribution, we present a framework based on neural networks that allows modeling of theuser’s intention during the dialogue and uses this prediction todynamically adapt the dialoguemodel of the system taking intoconsideration the user’s needs and preferences. We have evaluated our proposal to develop a user-adapted spoken dialogue systemthat facilitates tourist information and services and provide a detailed discussion of the positive influence of our proposal in thesuccess of the interaction, the information and services provided, and the quality perceived by the users.