We propose semantic role features for a Tree-to-String transducer to model the reordering/deletion of source-side semantic roles. These semantic features, as well as the Tree-to-S...
Extracting tree transducer rules for syntactic MT systems can be hindered by word alignment errors that violate syntactic correspondences. We propose a novel model for unsupervise...
The parameters of statistical translation models are typically estimated from sentence-aligned parallel corpora. We show that significant improvements in the alignment and transla...
Current MT systems, whatever translation method they at present employ, do not reach an optimum output on free text. Our hypothesis for the experiment reported in this paper is th...
A good decoding algorithm is critical to the success of any statistical machine translation system. The decoder's job is to find the translation that is most likely according...
Ulrich Germann, Michael Jahr, Kevin Knight, Daniel...