Paper: Filtering Syntactic Constraints for Statistical Machine Translation

ACL ID P10-2004
Title Filtering Syntactic Constraints for Statistical Machine Translation
Venue Annual Meeting of the Association of Computational Linguistics
Session Short Paper
Year 2010
Authors

Source language parse trees offer very useful but imperfect reordering constraints for statis- tical machine translation. A lot of effort has been made for soft applications of syntactic constraints. We alternatively propose the se- lective use of syntactic constraints. A classifier is built automatically to decide whether a node in the parse trees should be used as a reorder- ing constraint or not. Using this information yields a 0.8 BLEU point improvement over a full constraint-based system.