Neural machine translation (NMT) models are usually trained with the
word-level loss using the teacher forcing algorithm, which not only evaluates
the translation improperly but also suffers from exposure bias. Sequence-level
training under the reinforcement framework can mitigate the problems of the
word-level loss, but its performance is unstable due to the high variance of
the gradient estimation. On these grounds, we present a method with a
differentiable sequence-level training objective based on probabilistic n-gram
matching which can avoid the reinforcement framework. In addition, this method
performs greedy search in the training which uses the predicted words as
context just as at inference to alleviate the problem of exposure bias.
Experiment results on the NIST Chinese-to-English translation tasks show that
our method significantly outperforms the reinforcement-based algorithms and
achieves an improvement of 1.5 BLEU points on average over a strong baseline
system.

该研究提出一种基于可微序列级训练目标的方法，使用概率 n-gram 匹配来避免强化学习框架，该方法在训练中执行贪心搜索并使用预测的单词作为上下文，以缓解曝光偏差问题，实验结果表明，该方法在 NIST 中英文翻译任务中显着优于基于强化学习的算法，并在强基线系统上平均实现了 1.5 个 BLEU 点的改进。