Rethinking Representations: A Log-bilinear Model of Phonotactics
- Huteng Dai (Rutgers University)
- Connor Mayer (University of California, Irvine)
- Richard Futrell (University of California, Irvine)
Abstract
Models of phonotactics include subsegmental representations in order to generalize to unattested sequences. These representations can be encoded in at least two ways: as discrete, phonetically-based features, or as continuous, distribution-based representations induced from the statistical patterning of sounds. Because phonological theory typically assumes that representations are discrete, past work has reduced continuous representations to discrete ones, which eliminates potentially relevant information. In this paper we present a model of phonotactics that can use continuous representations directly, and show that this approach yields competitive performance on modeling experimental judgments of English sonority sequencing. The proposed model broadens the space of possible phonotactic models by removing requirements for discrete features, and is a step towards an integrated picture of phonotactic learning based on distributional statistics and continuous representations.
Keywords: phonology, phonological learning, continuous representation, phonotactics, sonority sequencing, machine learning
How to Cite:
Dai, H., Mayer, C. & Futrell, R., (2023) “Rethinking Representations: A Log-bilinear Model of Phonotactics”, Society for Computation in Linguistics 6(1), 259-268. doi: https://doi.org/10.7275/ebv1-5g73
Downloads:
Download PDF