论文标题
查找：双语词典改善神经机器翻译
Look It Up: Bilingual Dictionaries Improve Neural Machine Translation
论文作者
论文摘要
尽管神经机器翻译（NMT）质量取得了进步，但罕见的单词仍然存在问题。对于人类来说，解决稀有问题的解决方案长期以来一直是字典，但是词典不能直接纳入NMT。在本文中，我们描述了一种将字典定义“附加”到稀有单词的新方法，以便网络可以学习使用它们的最佳方法。我们证明了使用双语词典最多提高了1.8个BLEU。
Despite advances in neural machine translation (NMT) quality, rare words continue to be problematic. For humans, the solution to the rare-word problem has long been dictionaries, but dictionaries cannot be straightforwardly incorporated into NMT. In this paper, we describe a new method for "attaching" dictionary definitions to rare words so that the network can learn the best way to use them. We demonstrate improvements of up to 1.8 BLEU using bilingual dictionaries.
