Paper: Soft Dependency Constraints for Reordering in Hierarchical Phrase-Based Translation

ACL ID D11-1079
Title Soft Dependency Constraints for Reordering in Hierarchical Phrase-Based Translation
Venue Conference on Empirical Methods in Natural Language Processing
Session Main Conference
Year 2011
Authors

Long-distance reordering remains one of the biggest challenges facing machine translation. We derive soft constraints from the source de- pendency parsing to directly address the re- ordering problem for the hierarchical phrase- based model. Our approach significantly im- proves Chinese–English machine translation on a large-scale task by 0.84 BLEU points on average. Moreover, when we switch the tuning function from BLEU to the LRscore which promotes reordering, we observe total improvements of 1.21 BLEU, 1.30 LRscore and 3.36 TER over the baseline. On aver- age our approach improves reordering preci- sion and recall by 6.9 and 0.3 absolute points, respectively, and is found to be especially ef- fective for long-distance reodering.