Model M, a novel class-based exponential language model, has been shown to significantly outperform word n-gram models in state-of-the-art machine translation and speech recognit...
Finite-state Transducers (FST) can be very efficient to implement inter-dialectal transliteration. We illustrate this on the Hindi and Urdu language pair. FSTs can also be used fo...
M. G. Abbas Malik, Christian Boitet, Pushpak Bhatt...
Finding a proper distribution of translation probabilities is one of the most important factors impacting the effectiveness of a crosslanguage information retrieval system. In th...
Syntactic machine translation systems currently use word alignments to infer syntactic correspondences between the source and target languages. Instead, we propose an unsupervised...
Translation rule extraction is a fundamental problem in machine translation, especially for linguistically syntax-based systems that need parse trees from either or both sides of ...