PASCAL - Pattern Analysis, Statistical Modelling and Computational Learning

Monte Carlo techniques for phrase-based translation
Abhishek Arun, Chris Dyer, Barry Haddow, Phil Blunsom, Adam Lopez and Philipp Koehn
Machine Translation Volume 24, Number 2, pp. 103-121, 2010.

Abstract

Recent advances in statistical machine translation have used approximate beam search for 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 risk training and decoding.

EPrint Type:Article
Project Keyword:Project Keyword UNSPECIFIED
Subjects:Natural Language Processing
ID Code:7949
Deposited By:Phil Blunsom
Deposited On:17 March 2011