Exploitation of machine learning techniques in modelling phrase movements for machine translation
We propose a distance phrase reordering model (DPR) for statistical machine translation (SMT), where the aim is to learn the grammatical rules and context dependent changes using a phrase reordering classiﬁcation framework. We consider a variety of machine learning techniques, including state-of-the-art structured prediction methods. Techniques are compared and evaluated on a Chinese–English corpus, a language pair known for the high reordering characteristics which cannot be adequately captured with current models. For the reordering classiﬁcation task the methods clearly outperform the baseline and furthermore, when placed as a component in the state-of-the-art machine translation system MOSES, we demonstrated improved translation results over the current system.