A Connectionist account of Spanish determiner production

Abstract

A Connectionist Network that models the production of simple phonologically coded Spanish Noun Phrases is described. The training data uses type/token frequencies taken directly from a Spanish child's linguistic environment. The training set increases in size in a manner which mirrors the increasing complexity of the real linguistic environment. The results show that the model can learn the task and generalise to unseen Noun Phrase combinations. Moreover the generalisation performance is of a similar nature to that of Spanish children.