Describes a computer-based connectionist-type network model that correctly identified the gender of a set of French nouns, relying solely on information inherent in the nouns' structures, in the absence of explicit rules for evaluating nouns, through discovering criterial gender-specific features through examples of masculine and feminine nouns.…

Outlines a hierarchical model of acquisition of second-language phonology, based on the scrutinization of contexts and evocation of appropriate rules through contact situations in which a conflict emerges between the native and target phonologies. (23 references) (Author/CB)

Are words read visually (by means of a direct mapping from orthography to semantics) or phonologically (by mapping from orthography to phonology to semantics)? The authors addressed this long-standing debate by examining how a large-scale computational model based on connectionist principles would solve the problem and comparing the model's…

The authors present data from 2 feature verification experiments designed to determine whether distinctive features have a privileged status in the computation of word meaning. They use an attractor-based connectionist model of semantic memory to derive predictions for the experiments. Contrary to central predictions of the conceptual structure…