Paper: A Fast Fertility Hidden Markov Model for Word Alignment Using MCMC

ACL ID D10-1058
Title A Fast Fertility Hidden Markov Model for Word Alignment Using MCMC
Venue Conference on Empirical Methods in Natural Language Processing
Session Main Conference
Year 2010
Authors

A word in one language can be translated to zero, one, or several words in other languages. Using word fertility features has been shown to be useful in building word alignment mod- els for statistical machine translation. We built a fertility hidden Markov model by adding fer- tility to the hidden Markov model. This model not only achieves lower alignment error rate than the hidden Markov model, but also runs faster. It is similar in some ways to IBM Model 4, but is much easier to understand. We use Gibbs sampling for parameter estimation, which is more principled than the neighbor- hood method used in IBM Model 4.