Preference Grammars and Soft Syntactic Constraints for GHKM Syntax-based Statistical Machine Translation

摘要

In this work, we investigate the effectiveness of two techniques for a feature-based integration of syntactic information into GHKM string-to-tree statistical machine translation (Galley et al., 2004): (1.) Preference grammars on the target language side promote syntactic well-formedness during decoding while also allowing for derivations that are not linguistically motivated (as in hierarchical translation). (2.) Soft syntactic constraints augment the system with additional source-side syntax features while not modifying the set of string-to-tree translation rules or the baseline feature scores. We conduct experiments with a state-of-the-art setup on an English→German translation task. Our results suggest that preference grammars for GHKM translation are inferior to the plain target-syntactified model, whereas the enhancement with soft source syntactic constraints provides consistent gains. By employing soft source syntactic constraints with sparse features, we are able to achieve improvements of up to 0.7 points Bleu and 1.0 points Ter.