Paper: Model-Based Aligner Combination Using Dual Decomposition

ACL ID P11-1043
Title Model-Based Aligner Combination Using Dual Decomposition
Venue Annual Meeting of the Association of Computational Linguistics
Session Main Conference
Year 2011
Authors

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 pre- dictions of two directional models, typically using heuristic combination procedures like grow-diag-final. This paper presents a graph- ical model that embeds two directional align- ers into a single model. Inference can be per- formed via dual decomposition, which reuses the efficient inference algorithms of the direc- tional models. Our bidirectional model en- forces a one-to-one phrase constraint while ac- counting for the uncertainty in the underlying directional models. The resulting alignments improve upon baseline combi...