Recent advances in statistical machine translation have used beam search for approximate NP-complete inference within probabilistic translation models. We present an alternative approach of sampling from the posterior distribution defined by a translation model. We define a novel Gibbs sampler for sampling translations given a source sentence and show that it effectively explores this posterior distribution. In doing so we overcome the limitations of heuristic beam search and obtain theoretically sound solutions to inference problems such as finding the maximum probability translation and minimum expected risk training and decoding.
|Title of host publication||Proceedings of the Thirteenth Conference on Computational Natural Language Learning (CoNLL-2009)|
|Place of Publication||Boulder, Colorado|
|Publisher||Association for Computational Linguistics|
|Number of pages||9|
|Publication status||Published - 1 Jun 2009|