@article{östling_tiedemann_2016,
title={Efficient Word Alignment with Markov Chain Monte Carlo},
volume={106},
DOI={10.1515/pralin-2016-0013},
abstractNote={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.},
publisher={Walter de Gruyter GmbH},
author={Östling and Tiedemann},
year={2016},
month={Oct}
}