A Neural Reordering Model for Phrase-based Translation

Abstract

While lexicalized reordering models have been widely used in phrase-based translation systems, they suffer from three drawbacks: context insensitivity, ambiguity, and sparsity. We propose a neural reordering model that conditions reordering probabilities on the words of both the current and previous phrase pairs. Including the words of previous phrase pairs significantly improves context sensitivity and reduces reordering ambiguity. To alleviate the data sparsity problem, we build one classifier for all phrase pairs, which are represented as continuous space vectors. Ex-periments on the NIST Chinese-English datasets show that our neural reordering model achieves significant improvements over state-of-the-art lexicalized reordering models. 1