Bayesian Synchronous Grammar Induction

13 years 1 months ago
Bayesian Synchronous Grammar Induction
We present a novel method for inducing synchronous context free grammars (SCFGs) from a corpus of parallel string pairs. SCFGs can model equivalence between strings in terms of substitutions, insertions and deletions, and the reordering of sub-strings. We develop a non-parametric Bayesian model and apply it to a machine translation task, using priors to replace the various heuristics commonly used in this field. Using a variational Bayes training procedure, we learn the latent structure of translation equivalence through the induction of synchronous grammar categories for phrasal translations, showing improvements in translation performance over maximum likelihood models.
Phil Blunsom, Trevor Cohn, Miles Osborne
Added 29 Oct 2010
Updated 29 Oct 2010
Type Conference
Year 2008
Where NIPS
Authors Phil Blunsom, Trevor Cohn, Miles Osborne
Comments (0)