Connectionist psycholinguistics is an emerging approach to modeling empiric
al data on human language processing using connectionist computational arch
itectures. For almost 20 years, connectionist models have increasingly been
used to model empirical data across many areas of language processing. We
critically review four key areas: speech processing, sentence processing, l
anguage production, and reading aloud, and evaluate progress against three
criteria: data contact, task veridicality, and input representativeness. Re
cent connectionist modeling efforts have made considerable headway toward m
eeting these criteria, although it is by no means clear whether connectioni
st (or symbolic) psycholinguistics will eventually provide an integrated mo
del of full-scale human language processing.