Paper: Inducing Synchronous Grammars with Slice Sampling

ACL ID N10-1028
Title Inducing Synchronous Grammars with Slice Sampling
Venue Human Language Technologies
Session Main Conference
Year 2010
Authors

This paper describes an efficient sampler for synchronous grammar induction under a non- parametric Bayesian prior. Inspired by ideas from slice sampling, our sampler is able to draw samples from the posterior distributions of models for which the standard dynamic pro- graming based sampler proves intractable on non-trivial corpora. We compare our sampler to a previously proposed Gibbs sampler and demonstrate strong improvements in terms of both training log-likelihood and performance on an end-to-end translation evaluation.