Bayesian approaches have been shown to reduce the amount of overfitting that occurs when running the EM algorithm, by placing prior probabilities on the model parameters. We appl...
One style of Multi-Engine Machine Translation architecture involves choosing the best of a set of outputs from different systems. Choosing the best translation from an arbitrary s...
We reveal a previously unnoticed connection between dependency parsing and statistical machine translation (SMT), by formulating the dependency parsing task as a problem of word a...
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...
We present a first known result of high precision rare word bilingual extraction from comparable corpora, using aligned comparable documents and supervised classification. We in...