We present a novel paradigm for statistical machine translation (SMT), based on a joint modeling of word alignment and the topical aspects underlying bilingual document-pairs, via...
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 ...
In this paper, we describe a Web-based spoken translation game aimed at providing language learners with an easily accessible and fun environment to practice speaking the foreign l...
In statistical machine translation, single-word based models have an important deficiency; they do not take contextual information into account for the translation decision. A poss...
In this paper, we present a novel approach to enhance hierarchical phrase-based machine translation systems with linguistically motivated syntactic features. Rather than directly ...