Paper: Non-Projective Parsing for Statistical Machine Translation

ACL ID D09-1021
Title Non-Projective Parsing for Statistical Machine Translation
Venue Conference on Empirical Methods in Natural Language Processing
Session Main Conference
Year 2009
Authors

We describe a novel approach for syntax- based statistical MT, which builds on a variant of tree adjoining grammar (TAG). Inspired by work in discriminative depen- dency parsing, the key idea in our ap- proach is to allow highly flexible reorder- ing operations during parsing, in combina- tion with a discriminative model that can condition on rich features of the source- language string. Experiments on trans- lation from German to English show im- provements over phrase-based systems, both in terms of BLEU scores and in hu- man evaluations.