A Short-Term Memory Architecture for the Learning of Morphophonemic Rules
Michael Gasser, Chan-Do Lee · Neural Information Processing Systems · 1990
Despite its successes, Rumelhart and McClelland's (1986) well-known approach to the learning of morphophonemic rules suffers from two deficiencies: (1) It performs the artificial task of associating forms with forms rather than perception or production. (2) It is not constrained in ways that humans learners are. This paper describes a model which addresses both objections. Using a simple recurrent architecture which takes both forms and meanings as inputs, the model learns to generate verbs in one or another tense, given arbitrary meanings, and to recognize the tenses of verbs. Furthermore, it fails to learn reversal processes unknown in human language.