Empirical Tests of the Gradual Learning Algorithm
Paul Boersma, University of
Bruce Hayes, UCLA
Published 2001: Linguistic Inquiry 32: 45-86. Downloadable copy is the final prepublication version, July 2000.
The Gradual Learning Algorithm (Boersma 1997) is a constraint ranking algorithm for learning Optimality-theoretic grammars. The purpose of this article is to assess the capabilities of the Gradual Learning Algorithm, particularly in comparison with the Constraint Demotion algorithm of Tesar and Smolensky (1993, 1996, 1998, 2000), which initiated the learnability research program for Optimality Theory. We argue that the Gradual Learning Algorithm has a number of special advantages: it can learn free variation,deal effectively with noisy learning data, and account for gradient well-formedness judgments. The case studies we examine involve Ilokano reduplication and metathesis, Finnish genitive plurals, and the distribution of English light and dark /l /.
Graph: the function that converts differences in ranking values to ranking probabilities: