CONSYDERR: a two-level hybrid architecture for structuring knowledge for commonsense reasoning

This paper presents an architecture for structuring knowledge in vague and continuous domains for commonsense reasoning where similarity plays a large role in performing plausible inferences. The architecture consists of two levels: one is an inference network with nodes representing concepts and links representing rules connecting concepts, and the other is a microfeature based replica of the first level. Based on the interaction between the concept nodes and microfeature nodes in the architecture, inferences are facilitated and knowledge not explicitly encoded in a system can be deduced via a mixture of similarity matching and rule application. The architecture is able to take account of many important desiderata of plausible reasoning, and produces sensible conclusions accordingly