Paper: Bayesian Inference for Finite-State Transducers

ACL ID N10-1068
Title Bayesian Inference for Finite-State Transducers
Venue Human Language Technologies
Session Main Conference
Year 2010

We describe a Bayesian inference algorithm that can be used to train any cascade of weighted finite-state transducers on end-to- end data. We also investigate the problem of automatically selecting from among mul- tiple training runs. Our experiments on four different tasks demonstrate the genericity of this framework, and, where applicable, large improvements in performance over EM. We also show, for unsupervised part-of-speech tagging, that automatic run selection gives a large improvement over previous Bayesian ap- proaches.