LEARNING NOUNS AND ADJECTIVES - A CONNECTIONIST ACCOUNT

Why do children learn nouns such as cup faster than dimensional adject ives such as big? Most explanations of this phenomenon rely on prior k nowledge of the noun-adjective distinction or on the logical priority of nouns as the arguments of predicates. In this article we examine an alternative account, one which relies instead on properties of the se mantic categories to be learned and of the word-learning task itself. We isolate four such properties: The relative size, the relative compa ctness, and the degree of overlap of the regions in representational s pace associated with the categories, and the presence or absence of le xical dimensions (what colour) in the linguistic context of a word. In a set of five experiments, we trained a simple connectionist network to label input objects in particular linguistic contexts. The network learned categories resembling nouns with respect to the four propertie s faster than it learned categories resembling adjectives.