We investigate the impact of parse quality on a syntactically-informed statistical machine translation system applied to technical text. We vary parse quality by varying the amoun...
We present a set of algorithms that enable us to translate natural language sentences by exploiting both a translation memory and a statistical-based translation model. Our result...
Statistical machine translation is quite robust when it comes to the choice of input representation. It only requires consistency between training and testing. As a result, there ...
We introduce a semi-supervised approach to training for statistical machine translation that alternates the traditional Expectation Maximization step that is applied on a large tr...
Some Statistical Machine Translation systems never see the light because the owner of the appropriate training data cannot release them, and the potential user of the system canno...