Deductive Inference in the Context of the Dialogue Process

The paper is devoted to the investigation of a community between the dialogue process and the process of deductive inference. Attention is focused on the goal-oriented interactive process between two agents (active and reactive) involved into a step-by-step question-answering dialogue, which is considered as an activity directed to solving certain problem. A key element of the architecture of Dialogue Problem Solver is Dialogue Knowledge Base (DiKB). The paper demonstrates how an inference process of the classical rule-based systems can be emulated by navigation within DiKB. Some positive features of such emulation are discussed. Final section represents a formal theory of the DiKB structure from the inference process point of view. In conclusion the idea of a knowledge base agent with distributed architecture is discussed.