Paper: Using Feature Structures to Improve Verb Translation in English-to-German Statistical MT

ACL ID W14-1005
Title Using Feature Structures to Improve Verb Translation in English-to-German Statistical MT
Venue Workshop on Hybrid Approaches to Translation
Session
Year 2014
Authors

SCFG-based statistical MT models have proven effective for modelling syntactic aspects of translation, but still suffer prob- lems of overgeneration. The production of German verbal complexes is particu- larly challenging since highly discontigu- ous constructions must be formed con- sistently, often from multiple independent rules. We extend a strong SCFG-based string-to-tree model to incorporate a rich feature-structure based representation of German verbal complex types and com- pare verbal complex production against that of the reference translations, finding a high baseline rate of error. By developing model features that use source-side infor- mation to influence the production of ver- bal complexes we are able to substantially improve the type accuracy as compared to the reference.