We present a quasi-synchronous dependency grammar (Smith and Eisner, 2006) for machine translation in which the leaves of the tree are phrases rather than words as in previous wor...
Hindi and Urdu share a common phonology, morphology and grammar but are written in different scripts. In addition, the vocabularies have also diverged significantly especially in ...
Language modeling for an inflected language such as Arabic poses new challenges for speech recognition and machine translation due to its rich morphology. Rich morphology results i...
Tree based translation models are a compelling means of integrating linguistic information into machine translation. Syntax can inform lexical selection and reordering choices and...
This paper proposes a two-phase example-based machine translation methodology which develops translation templates from examples and then translates using template matching. This ...