Paper: Syntactic SMT Using a Discriminative Text Generation Model

ACL ID D14-1021
Title Syntactic SMT Using a Discriminative Text Generation Model
Venue Conference on Empirical Methods in Natural Language Processing
Session Main Conference
Year 2014
Authors

We study a novel architecture for syntactic SMT. In contrast to the dominant approach in the literature, the system does not rely on translation rules, but treat translation as an unconstrained target sentence gen- eration task, using soft features to cap- ture lexical and syntactic correspondences between the source and target languages. Target syntax features and bilingual trans- lation features are trained consistently in a discriminative model. Experiments us- ing the IWSLT 2010 dataset show that the system achieves BLEU comparable to the state-of-the-art syntactic SMT systems.