Magri 2016: Error-driven learning in OT and HG: a comparison
The OT error-driven learner is known to admit guarantees of efficiency, stochastic tolerance and noise robustness which hold independently of any substantive assumptions on the constraints. This paper shows that the HG learner instead does not admit such constraint-independent guarantees. The HG theory of error-driven learning thus needs to be substantially restricted to specific constraint sets.
|Format:||[ pdf ]|
(please use that when you cite this article, unless you want to cite the full url: http://ling.auf.net/lingbuzz/002843)
|keywords:||learnability, error-driven learning, ot, hg, phonology|