Neural Machine Translation of Logographic Languages Using Sub-character Level Information
This addresses a specific bottleneck in NMT for logographic languages, offering incremental improvements by leveraging shared sub-character units.
The study tackled the problem of neural machine translation for logographic languages by incorporating sub-character level information, resulting in improved translation performance for Chinese-English and Chinese-Japanese pairs.
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.