Generic Command Interpretation Algorithms for Conversational Agents

This paper focuses on the human-machine communication within the framework of intelligent agents. We propose a generic architecture provided with a natural language (NL) algorithm for command interpretation that can be adapted to different agent´s domains. Our NL architecture only depends on the agent´s code and its domain ontology. We consider two classical approaches for NL command interpretation: the top-down approach, which relies on the agent´s model syntactical constraints, and the bottom-up approach which relies on the set of the agent´s possible actions. We propose to combine both approaches in a bottom-up based algorithm that makes use of agent´s constraints. We propose a comparative evaluation of these three algorithms.