Paper: Tailoring Word Alignments to Syntactic Machine Translation

ACL ID P07-1003
Title Tailoring Word Alignments to Syntactic Machine Translation
Venue Annual Meeting of the Association of Computational Linguistics
Session Main Conference
Year 2007
Authors

Extracting tree transducer rules for syntac- tic MT systems can be hindered by word alignment errors that violate syntactic corre- spondences. We propose a novel model for unsupervised word alignment which explic- itly takes into account target language con- stituent structure, while retaining the robust- ness and efficiency of the HMM alignment model. Our model’s predictions improve the yield of a tree transducer extraction system, without sacrificing alignment quality. We also discuss the impact of various posterior- based methods of reconciling bidirectional alignments.