Adaptive dialogue management using intent clustering and fuzzy rules

Abstract

Conversational systems have become an element of everyday life for billions of users who use speech-based interfaces to services, engage with personal digital assistants on smartphones, social media chatbots, or smart speakers. One of the most complex tasks in the development of these systems is to design the dialogue model, the logic that provided a user input selects the next answer. The dialogue model must also consider mechanisms to adapt the response of the system and the interaction style according to different groups and user profiles. Rule-based systems are difficult to adapt to phenomena that were not taken into consideration at design-time. However, many of the systems that are commercially available are based on rules, and so are the most widespread tools for the development of chatbots and speech interfaces. In this article, we present a proposal to: (a) automatically generate the dialogue rules from a dialogue corpus through the use of evolving algorithms, (b) adapt the rules according to the detected user intention. We have evaluated our proposal with several conversational systems of different application domains, from which our approach provided an efficient way for adapting a set of dialogue rules considering user utterance clusters.

Towards conversational technology to promote, monitor and protect mental health

“…This will be achieved by means of a rich user model based on the user's objectives and engagement, challenges that are pervasive to different types of multimodal ecoaches [6]. Adaptive, trustworthy dialogue management will be key to this task [7,8], for which different models will be put in place an evolved as more data is available [9,10]. In relation to this, we are conducting several studies related to the acceptance of different aspects of the interaction with a conversational system in multiple settings.…”