Encoding Knowledge In Partitioned Networks

Abstract

This paper discusses network notations for encoding a number of different kinds of knowledge, including taxonomic information; general statements involving quantification; information about processes and procedures; the delineation of local contexts, beliefs, and wishes; and the relationships between syntactic units and their interpretations. Many of the encodings appeal to the concept of network partitioning, in which a large net is partitioned into subnets and higher-order relationships among the subnets are defined. Procedural mechanisms for constructing and using the various network formalisms are discussed as equal partners with the declarative structures.