Examines cognates (lexical items from different languages that are identified by bilinguals as being the same thing), arguing that the Cohort Model effectively explains cognate properties and that cognates should be defined in terms of their structural representations and the processes that activate and select them. (79 references) (Author/CB)

Criticizes the computer modelling experiments conducted by Sokolik and Smith (1992), which involved the learning of French gender attribution using connectionist architecture. The article argues that the experiments greatly oversimplified the complexity of gender learning, in that they were designed in such a way that knowledge that must be…