Model-Based Aligner Combination Using Dual Decomposition
Venue
Proceedings of the Association for Computational Linguistics (ACL), 2011
Publication Year
2011
Authors
BibTeX
Abstract
Unsupervised word alignment is most often modeled as a Markov process that
generates a sentence f conditioned on its translation e. A similar model generating
e from f will make different alignment predictions. Statistical machine translation
systems combine the predictions of two directional models, typically using
heuristic combination procedures like grow-diag-final. This paper presents a
graphical model that embeds two directional aligners into a single model. Inference
can be performed via dual decomposition, which reuses the efficient inference
algorithms of the directional models. Our bidirectional model enforces a one-to-one
phrase constraint while accounting for the uncertainty in the underlying
directional models. The resulting alignments improve upon baseline combination
heuristics in word-level and phrase-level evaluations.
