Paper: Factored Soft Source Syntactic Constraints for Hierarchical Machine Translation

ACL ID D13-1053
Title Factored Soft Source Syntactic Constraints for Hierarchical Machine Translation
Venue Conference on Empirical Methods in Natural Language Processing
Session Main Conference
Year 2013
Authors

This paper describes a factored approach to incorporating soft source syntactic constraints into a hierarchical phrase-based translation system. In contrast to traditional approaches that directly introduce syntactic constraints to translation rules by explicitly decorating them with syntactic annotations, which often ex- acerbate the data sparsity problem and cause other problems, our approach keeps transla- tion rules intact and factorizes the use of syn- tactic constraints through two separate mod- els: 1) a syntax mismatch model that asso- ciates each nonterminal of a translation rule with a distribution of tags that is used to measure the degree of syntactic compatibil- ity of the translation rule on source spans; 2) a syntax-based reordering model that predicts whether a pair of sibl...