Efficient Word Alignment with Markov Chain Monte Carlo
Open Access
- 1 October 2016
- journal article
- research article
- Published by Walter de Gruyter GmbH in The Prague Bulletin of Mathematical Linguistics
- Vol. 106 (1) , 125-146
Abstract
We present EFMARAL, a new system for efficient and accurate word alignment using a Bayesian model with Markov Chain Monte Carlo (MCMC) inference. Through careful selection of data structures and model architecture we are able to surpass the fast_align system, commonly used for performance-critical word alignment, both in computational efficiency and alignment accuracy. Our evaluation shows that a phrase-based statistical machine translation (SMT) system produces translations of higher quality when using word alignments from EFMARAL than from fast_align, and that translation quality is on par with what is obtained using GIZA++, a tool requiring orders of magnitude more processing time. More generally we hope to convince the reader that Monte Carlo sampling, rather than being viewed as a slow method of last resort, should actually be the method of choice for the SMT practitioner and others interested in word alignment.Keywords
This publication has 11 references indexed in Scilit:
- Improving Statistical Machine Translation Using Bayesian Word Alignment and Gibbs SamplingIEEE Transactions on Audio, Speech, and Language Processing, 2013
- Measuring Word Alignment Quality for Statistical Machine TranslationComputational Linguistics, 2007
- Symmetric word alignments for statistical machine translation2004
- A Systematic Comparison of Various Statistical Alignment ModelsComputational Linguistics, 2003
- Statistical phrase-based translation2003
- An evaluation exercise for word alignment2003
- Inducing multilingual text analysis tools via robust projection across aligned corpora2001
- The two-parameter Poisson-Dirichlet distribution derived from a stable subordinatorThe Annals of Probability, 1997
- Maximum Likelihood from Incomplete Data Via the EM AlgorithmJournal of the Royal Statistical Society Series B: Statistical Methodology, 1977
- Conditional Expectation and Unbiased Sequential EstimationThe Annals of Mathematical Statistics, 1947