Convergence properties of a gradual learning algorithm for Harmonic Grammar

Abstract

This paper investigates a gradual on-line learning algorithm for Harmonic Grammar. By adapting existing convergence proofs for perceptrons, we show that for any nonvarying target language, Harmonic-Grammar learners are guaranteed to converge to an appropriate grammar, if they receive complete information about the structure of the learning data. We also prove convergence when the learner incorporates evaluation noise, as in Stochastic Optimality Theory. Computational tests of the algorithm show that it converges quickly. When learners receive incomplete information (e.g. some structure remains hidden), tests indicate that the algorithm is more likely to converge than two comparable Optimality-Theoretic learning algorithms.