[Author Login]
Title:Maximum Entropy Models and Stochastic Optimality Theory
Authors:Gerhard Jaeger
Abstract:The paper compares Stochastic OT (StOT) in the sense of Paul Boersma's work with Maximum Entropy (ME) models. I show that Boersma's Gradual Learning Algorithm (GLA) for StOT is applicable to ME models as well. The combination of the GLA with ME models is similar to StOT as far as empirical coverage is concerned, but has several theoretical advantages. Most importantly, GLA is guaranteed to converge if combined with ME evaluation.
Type:Paper/tech report
Area/Keywords:Computation,Learnability,Formal Analysis
Article:Version 1