Paper

Constraint breeding during on-line incremental learning

---

Abstract

An evolutionary algorithm for simultaneously inducing and weighting phonological constraints (the Winnow-MaxEnt-Subtree Breeder) is described, analyzed, and illustrated. Implementing weights as sub-population sizes, reproduction with selection executes a new variant of Winnow (Littleton 1988), which is shown to converge. A flexible constraint schema, based on the same prosodic and autosegmental trees used in representations, is described, together with algorithms for mutation and recombination (mating). The algorithm is applied to explaining abrupt learning curves, and predicts an empirical connection between abruptness and language-particularity.

Keywords: phonology, learning, Winnow, evolutionary algorithm, Maximum Entropy, abruptness

How to Cite:

Moreton, E., (2019) “Constraint breeding during on-line incremental learning”, Society for Computation in Linguistics 2(1), 69-80. doi: https://doi.org/10.7275/6f9x-6411