We motivate and define the XSIL language as a flexible, hierarchical, extensible transport language for scientific data objects. The entire object may be represented in the file, o...
Kent Blackburn, Albert Lazzarini, Thomas A. Prince...
Hierarchical phrase-based models provide a powerful mechanism to capture non-local phrase reorderings for statistical machine translation (SMT). However, many phrase reorderings a...
The deep Boltzmann machine is a powerful model that extracts the hierarchical structure of observed data. While inference is typically slow due to its undirected nature, we argue ...
In this work, we propose two extensions of standard word lexicons in statistical machine translation: A discriminative word lexicon that uses sentence-level source information to ...
Certain distinctions made in the lexicon of one language may be redundant when translating into another language. We quantify redundancy among source types by the similarity of th...