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 ...
We introduce SPMT, a new class of statistical Translation Models that use Syntactified target language Phrases. The SPMT models outperform a state of the art phrase-based baseline...
Daniel Marcu, Wei Wang, Abdessamad Echihabi, Kevin...
This paper describes an alternative translation model based on a text chunk under the framework of statistical machine translation. The translation model suggested here first per...
We describe a new pruning approach to remove phrase pairs from translation models of statistical machine translation systems. The approach applies the original translation system ...
In this paper, several approaches for language portability of dialogue systems are investigated with a focus on the spoken language understanding (SLU) component. We show that the...