2007. Experiments in domain adaptation for statistical machine translation

The special challenge of the WMT 2007 shared task was domain adaptation. We took this opportunity to experiment with various ways of adapting a statistical ma-chine translation systems to a special do-main (here: news commentary), when most of the training data is from a dif-ferent domain (here: European Parliament speeches). This paper also gives a descrip-tion of the submission of the University of Edinburgh to the shared task. 1 Our framework: the Moses MT system The open source Moses (Koehn et al., 2007) MT system was originally developed at the Universit