The distortion cost function used in Mosesstyle machine translation systems has two flaws. First, it does not estimate the future cost of known required moves, thus increasing sea...
Spence Green, Michel Galley, Christopher D. Mannin...
Typical statistical machine translation systems are trained with static parallel corpora. Here we account for scenarios with a continuous incoming stream of parallel training data...
Abby Levenberg, Chris Callison-Burch, Miles Osborn...
Reordering is currently one of the most important problems in statistical machine translation systems. This paper presents a novel strategy for dealing with it: statistical machin...
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...
In this paper we investigate the challenges of applying statistical machine translation to meeting conversations, with a particular view towards analyzing the importance of modeli...