Convergence Properties of a Gradual Learning Algorithm for Harmonic Grammar
نویسندگان
چکیده
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.
منابع مشابه
HG has no computational advantages over OT: consequences for the theory of OT online algorithms
Various authors have recently endorsed Harmonic Grammar (HG) as a replacement of Optimality Theory (OT). One argument for this move is based on computational considerations: OT looks prima facie like an exotic framework with no correspondent in Machine Learning, and the replacement with HG allows methods and results form Machine Learning to be imported within Computational Phonology; see for in...
متن کاملProbabilistic Learning Algorithms and Optimality Theory
This paper provides a critical assessment of the Gradual Learning Algorithm (GLA) for probabilistic optimality-theoretic grammars proposed by Boersma and Hayes (2001). After a short introduction to the problem of grammar learning in OT, we discuss the limitations of the standard solution to this problem (the Constraint Demotion Algorithm by Tesar and Smolensky (1998)), and outline how the GLA a...
متن کاملHarmonics Estimation in Power Systems using a Fast Hybrid Algorithm
In this paper a novel hybrid algorithm for harmonics estimation in power systems is proposed. The estimation of the harmonic components is a nonlinear problem due to the nonlinearity of phase of sinusoids in distorted waveforms. Most researchers implemented nonlinear methods to extract the harmonic parameters. However, nonlinear methods for amplitude estimation increase time of convergence. Hen...
متن کاملCreating Algorithmic Symbols to Enhance Learning English Grammar
This paper introduces a set of English grammar symbols that the author has developed to enhance students’ understanding and consequently, application of the English grammar rules. A pretest-posttest control-group design was carried out in which the samples were students in two girls’ senior high schools (N=135, P ≤ 0.05) divided into two groups: the Treatment which received gramm...
متن کامل