Statistical Learning Theory and Linguistic Typology: a Learnability Perspective on OT’s Strict Domination
- Émile Enguehard (École Normale Supérieure)
- Edward Flemming (MIT)
- Giorgio Magri (CNRS)
Abstract
This paper develops a learnability argument for strict domination by looking at the generalization error of learners trained on OT and HG target grammars. The argument is based on both a review of error bounds in the recent statistical learning literature and simulation results on realistic phonological test cases.
Keywords: constraint-based phonology, Harmonic Grammar, strict domination, learnability, generalization error, binary classification
How to Cite:
Enguehard, É., Flemming, E. & Magri, G., (2018) “Statistical Learning Theory and Linguistic Typology: a Learnability Perspective on OT’s Strict Domination”, Society for Computation in Linguistics 1(1), 1-11. doi: https://doi.org/10.7275/R5BP010Z
Downloads:
Download PDF