We describe an open-source toolkit for statistical machine translation whose novel contributions are (a) support for linguistically motivated factors, (b) confusion network decodi...
Philipp Koehn, Hieu Hoang, Alexandra Birch, Chris ...
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...
HMM-based models are developed for the alignment of words and phrases in bitext. The models are formulated so that alignment and parameter estimation can be performed efficiently....
We present a new open source toolkit for phrase-based and syntax-based machine translation. The toolkit supports several state-of-the-art models developed in statistical machine t...
In this paper, we present a novel global reordering model that can be incorporated into standard phrase-based statistical machine translation. Unlike previous local reordering mod...