Modelling message handling system

Abstract

This paper introduces a new approach to designing a Message Handling Assistant (MA). It provides a generic model of an MA and an intention extraction function for text messages using speech act theory and the belief-desire-intention (BDI) model of rational agency. The model characterizes the desired behaviors of an MA and the relationships between the MA, its user, and other human agents with whom the user interacts through message exchange. The intention extraction function formulates intentions from performatives identified by a probabilistic dialogue act classifier using constraints for felicitous human communication. This paper also proposes a semantic communication framework which integrates key agent and Internet technologies for composing and exchanging semantic messages.