Monte carlo inference and maximization for phrase-based translation

Authors:
Abhishek Arun;Chris Dyer;Barry Haddow;Phil Blunsom;Adam Lopez;Philipp Koehn
Affiliations:
University of Edinburgh, Edinburgh, UK;University of Maryland, College Park, MD;University of Edinburgh, Edinburgh, UK;University of Edinburgh, Edinburgh, UK;University of Edinburgh, Edinburgh, UK;University of Edinburgh, Edinburgh, UK
Venue:
CoNLL '09 Proceedings of the Thirteenth Conference on Computational Natural Language Learning
Year:
2009

Citing 14
Cited 5

Local Gain Adaptation in Stochastic Gradient Descent

Local Gain Adaptation in Stochastic Gradient Descent
The mathematics of statistical machine translation: parameter estimation

Computational Linguistics - Special issue on using large corpora: II
A comparison of alignment models for statistical machine translation

COLING '00 Proceedings of the 18th conference on Computational linguistics - Volume 2
Computational complexity of probabilistic disambiguation by means of tree-grammars

COLING '96 Proceedings of the 16th conference on Computational linguistics - Volume 2
Fast decoding and optimal decoding for machine translation

ACL '01 Proceedings of the 39th Annual Meeting on Association for Computational Linguistics
BLEU: a method for automatic evaluation of machine translation

ACL '02 Proceedings of the 40th Annual Meeting on Association for Computational Linguistics
Statistical phrase-based translation

NAACL '03 Proceedings of the 2003 Conference of the North American Chapter of the Association for Computational Linguistics on Human Language Technology - Volume 1
Minimum error rate training in statistical machine translation

ACL '03 Proceedings of the 41st Annual Meeting on Association for Computational Linguistics - Volume 1
A phrase-based, joint probability model for statistical machine translation

EMNLP '02 Proceedings of the ACL-02 conference on Empirical methods in natural language processing - Volume 10
A better N-best list: practical determinization of weighted finite tree automata

HLT-NAACL '06 Proceedings of the main conference on Human Language Technology Conference of the North American Chapter of the Association of Computational Linguistics
Minimum risk annealing for training log-linear models

COLING-ACL '06 Proceedings of the COLING/ACL on Main conference poster sessions
Moses: open source toolkit for statistical machine translation

ACL '07 Proceedings of the 45th Annual Meeting of the ACL on Interactive Poster and Demonstration Sessions
Solving the problem of cascading errors: approximate Bayesian inference for linguistic annotation pipelines

EMNLP '06 Proceedings of the 2006 Conference on Empirical Methods in Natural Language Processing
Sampling alignment structure under a Bayesian translation model

EMNLP '08 Proceedings of the Conference on Empirical Methods in Natural Language Processing

A unified approach to minimum risk training and decoding

WMT '10 Proceedings of the Joint Fifth Workshop on Statistical Machine Translation and MetricsMATR
Monte Carlo techniques for phrase-based translation

Machine Translation
SampleRank training for phrase-based machine translation

WMT '11 Proceedings of the Sixth Workshop on Statistical Machine Translation
Cardinality pruning and language model heuristics for hierarchical phrase-based translation

Machine Translation
Document-wide decoding for phrase-based statistical machine translation

EMNLP-CoNLL '12 Proceedings of the 2012 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning

Quantified Score

Hi-index	0.00

Visualization

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.