An architectural framework for natural language interfaces to agent systems

In this paper, we describe an architectural framework for the development of natural language interfaces to agent systems. Since the communication between human and artificial agents is mostly task-related, the focus of the suggested architecture is on action representations as core structure and thread in the overall processing. The architectural framework we suggest is based on various forms of action representations and consists of a sequence of transformations, which converts the user’s verbal input into a suitable set of agent actions to produce a response to the input. This process reduces stepwise the complexity and ambiguity of the natural language input by using predefined sets of interim actions at different levels, and thus increases the robustness and reliability of the natural language interface. The architecture was employed in the design of several natural language interfaces to agent systems.