Paper

Evolving constraints and rules in Harmonic Grammar

Author: Elliott Moreton (University of North Carolina, Chapel Hill)

Abstract

An evolutionary model of pattern learning in the MaxEnt OT/HG framework is described in which constraint induction and constraint weighting are consequences of reproduction with variation and differential fitness. The model is shown to fit human data from published experiments on both unsupervised phonotactic and supervised visual pattern learning, and to account for the observed reversal in difficulty order of exclusive-or vs. gang-effect patterns between the two experiments. Different parameter settings are shown to yield gradual, parallel, connectionist- and abrupt, serial, symbolic-like performance.

Keywords: Harmonic Grammar, evolutionary computing, concept learning, Winnow algorithm, pattern learning, phonology, Feature Geometry

How to Cite: Moreton, E. (2020) “Evolving constraints and rules in Harmonic Grammar”, Society for Computation in Linguistics. 3(1). doi: https://doi.org/10.7275/3y0f-j559