We show for the first time that incorporating the predictions of a word sense disambiguation system within a typical phrase-based statistical machine translation (SMT) model cons...
Often, Statistical Machine Translation (SMT) between English and Korean suffers from null alignment. Previous studies have attempted to resolve this problem by removing unnecessar...
This paper describes the framework of the StatCan Daily Translation Extraction System (SDTES), a computer system that maps and compares webbased translation texts of Statistics Can...
Factored Statistical Machine Translation extends the Phrase Based SMT model by allowing each word to be a vector of factors. Experiments have shown effectiveness of many factors, ...
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...