论文标题
神经机器翻译的多层表示融合
Multi-layer Representation Fusion for Neural Machine Translation
论文作者
论文摘要
神经机器翻译系统需要许多堆叠层才能进行深层模型。但是预测取决于最高层的句子表示，而无需访问低级表示。这使得训练模型并构成信息损失的风险更加困难。在本文中，我们提出了一种多层表示融合（MLRF）方法来融合堆叠层。特别是，我们设计了三个融合功能，以从堆栈中学习更好的表示。实验结果表明，在IWSLT德语英语和NIST中文 - 英语MT任务上，我们的方法在强劲的变压器基线上的提高了0.92和0.56 BLEU点。结果是德语 - 英语翻译的最新最新。
Neural machine translation systems require a number of stacked layers for deep models. But the prediction depends on the sentence representation of the top-most layer with no access to low-level representations. This makes it more difficult to train the model and poses a risk of information loss to prediction. In this paper, we propose a multi-layer representation fusion (MLRF) approach to fusing stacked layers. In particular, we design three fusion functions to learn a better representation from the stack. Experimental results show that our approach yields improvements of 0.92 and 0.56 BLEU points over the strong Transformer baseline on IWSLT German-English and NIST Chinese-English MT tasks respectively. The result is new state-of-the-art in German-English translation.
