Abstract
Recent neural machine translation (NMT) systems have been greatly improved by encoder-decoder models with attention mechanisms and sub-word units. However, important differences between languages with logographic and alphabetic writing systems have long been overlooked. This study focuses on these differences and uses a simple approach to improve the performance of NMT systems utilizing decomposed sub-character level information for logographic languages. Our results indicate that our approach not only improves the translation capabilities of NMT systems between Chinese and English, but also further improves NMT systems between Chinese and Japanese, because it utilizes the shared information brought by similar sub-character units.
Abstract (translated)
最近的神经机器翻译（NMT）系统已通过具有关注机制和子字单元的编码器 - 解码器模型得到极大改进。然而，长期以来一直忽视语言与字母和字母书写系统之间的重要差异。本研究关注这些差异，并使用一种简单的方法来提高NMT系统的性能，利用分解的子字符级信息进行语标语言。我们的研究结果表明，我们的方法不仅提高了汉语和英语之间NMT系统的翻译能力，而且进一步改善了汉语和日语之间的NMT系统，因为它利用了类似子字符单元带来的共享信息。
URL
https://arxiv.org/abs/1809.02694
