We present a novel machine translation model which models translation by a linear sequence of operations. In contrast to the "N-gram" model, this sequence includes not only translation but also reordering operations. Key ideas of our model are (ⅰ) a new reordering approach which better restricts the position to which a word or phrase can be moved, and is able to handle short and long distance re-orderings in a unified way, and (ⅱ) a joint sequence model for the translation and reordering probabilities which is more flexible than standard phrase-based MT. We observe statistically significant improvements in BLEU over Moses for German-to-English and Spanish-to-English tasks, and comparable results for a French-to-English task.
展开▼
