Beyond is-a and part-whole: More semantic network links

AbstractSemantic networks need many more links than traditional ones include if they are to function as adequate models of human memory. Many tasks benefit from cognitively realistic representations. Such cognitively realistic models of human reasoning processes require a deep understanding of the logical properties of their links. This paper argues for three basic claims. First, we must identify the links that are fundamental to human cognitive processes. Second, we must understand how their logical properties are actually used in common sense reasoning. Third, even though the resulting properties are not nearly as neat as those of their as neat as those better known mathematical counterparts, we must investigate and use those properties if we want our systems to be representationaly adequate. This paper presents analyses of three links, and in the process demonstrates a methodology for dealing with these issues