Neural Machine Translation of Logographic Language Using Sub-character Level Information
Neural Machine Translation of Logographic Language Using Sub-character Level Information
复制标题
DOI：
10.18653/v1/w18-6303
复制
发表时间：
2018-09
期刊：
影响因子：
--
通讯作者：
Longtu Zhang;Mamoru Komachi
中科院分区：
文献类型：
--
作者：
Longtu Zhang;Mamoru Komachi
基于注意机制和子词单元的编码器-解码器模型大大改进了神经机器翻译系统。然而，具有符号和字母书写系统的语言之间的重要差异长期以来一直被忽视。本研究的重点是这些差异，并使用一种简单的方法来提高NMT系统的性能，该系统利用分解的子字符级别的信息来表示语言。结果表明，由于该方法利用了相似子字符单元带来的共享信息，不仅提高了中英NMT系统的翻译能力，而且进一步提高了中日NMT系统的翻译能力。
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.