Monte Carlo inference and maximization for phrase-based translation

Abhishek Arun, Chris Dyer, Barry Haddow, Phil Blunsom, Adam Lopez, Philipp Koehn

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

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.
Original languageEnglish
Title of host publicationProceedings of the Thirteenth Conference on Computational Natural Language Learning (CoNLL-2009)
Place of PublicationBoulder, Colorado
PublisherAssociation for Computational Linguistics
Pages102-110
Number of pages9
Publication statusPublished - 1 Jun 2009

Fingerprint Dive into the research topics of 'Monte Carlo inference and maximization for phrase-based translation'. Together they form a unique fingerprint.

Cite this