摘要：This paper discusses two ways in which the geometry of a semantic map can be defined: on the basis of a set of cross-linguistic data or on the basis of a semantic analysis of the meanings involved. I will argue that under a purely "data-driven" approach certain important aspects of contiguity in semantic maps, like exceptions and family resemblance structure, remain unclear and that we can get more insight into these aspects when working from a semantically defined geometry. The two approaches can complement each other in the use of semantic maps.
