How Transformer Revitalizes Character-based Neural Machine Translation: An Investigation on Japanese-Vietnamese Translation Systems

• Main Authors: Ngo, Thi-Vinh, Ha, Thanh-Le, Nguyen, Phuong-Thai, Nguyen, Le-Minh
• Format: Journal Article
• Language: English
• Published: 17-10-2019
• Subjects: Computer Science - Computation and Language
• DOI: 10.48550/arxiv.1910.02238

16th International Workshop on Spoken Language Translation 2019 While translating between East Asian languages, many works have discovered
clear advantages of using characters as the translation unit. Unfortunately,
traditional recurrent neural machine translation systems hinder the practical
usage of those character-based systems due to their architectural limitations.
They are unfavorable in handling extremely long sequences as well as highly
restricted in parallelizing the computations. In this paper, we demonstrate
that the new transformer architecture can perform character-based translation
better than the recurrent one. We conduct experiments on a low-resource
language pair: Japanese-Vietnamese. Our models considerably outperform the
state-of-the-art systems which employ word-based recurrent architectures.