Lexicality and pronunciation in a simulated neural net
William A. Phillips, I. M. Hay, Leslie S. Smith · British Journal of Mathematical and Statistical Psychology · 1993
Self‐supervised compressive neural nets can perform nonlinear multilevel latent structure analysis. They therefore have promise for cognitive theory. We study their use in the Seidenberg & McClelland (1989) model of reading. Analysis shows that self‐supervised compression in their model can make only a limited contribution to lexical decision, and simulation shows that it interferes with the associative mapping into phonology. Self‐supervised compression is therefore put to no good use in their model. This does not weaken the arguments for self‐supervised compression, however, and we suggest possible beneficial uses that merit further study.