A Markov language learning model for finite parameter spaces
Partha Niyogi, Robert C. Berwick · 1994
This paper shows how to formally characterize language learning in a finite parameter space as a Markov structure. Important new language learning results follow directly: explicitly calculated sample complexity learning times under different input distribution assumptions (inclding CHILDES database language input) and learning regimes. We also briefly describe a new way to formally model (rapid) diachronic syntax change.