Tree Adjoining Grammars have well-known advantages, but are typically considered too difficult for practical systems. We demonstrate that, when done right, adjoining improves tran...
As a principled approach to capturing semantic relations of words in information retrieval, statistical translation models have been shown to outperform simple document language m...
We describe a novel approach to machine translation that combines the strengths of the two leading corpus-based approaches: Phrasal SMT and EBMT. We use a syntactically informed d...
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...
We describe experiments carried out with adaptive language and translation models in the context of an interactive computer-assisted translation program. We developed cache-based ...
Laurent Nepveu, Guy Lapalme, Philippe Langlais, Ge...