Neural machine translation: A review of methods, resources, and tools

Zhixing Tan; Shuo Wang; Zonghan Yang; Gang Chen; Xuancheng Huang; Maosong Sun; Yang Liu

AI Open (Jan 2020)

Neural machine translation: A review of methods, resources, and tools

Zhixing Tan,
Shuo Wang,
Zonghan Yang,
Gang Chen,
Xuancheng Huang,
Maosong Sun,
Yang Liu

Affiliations

Zhixing Tan: Department of Computer Science and Technology, Tsinghua University, China; Institute for Artificial Intelligence, China; Beijing National Research Center for Information Science and Technology, China
Shuo Wang: Department of Computer Science and Technology, Tsinghua University, China; Institute for Artificial Intelligence, China; Beijing National Research Center for Information Science and Technology, China
Zonghan Yang: Department of Computer Science and Technology, Tsinghua University, China; Institute for Artificial Intelligence, China; Beijing National Research Center for Information Science and Technology, China
Gang Chen: Department of Computer Science and Technology, Tsinghua University, China; Institute for Artificial Intelligence, China; Beijing National Research Center for Information Science and Technology, China
Xuancheng Huang: Department of Computer Science and Technology, Tsinghua University, China; Institute for Artificial Intelligence, China; Beijing National Research Center for Information Science and Technology, China
Maosong Sun: Department of Computer Science and Technology, Tsinghua University, China; Institute for Artificial Intelligence, China; Beijing National Research Center for Information Science and Technology, China; Beijing Academy of Artificial Intelligence, China
Yang Liu: Department of Computer Science and Technology, Tsinghua University, China; Institute for AI Industry Research, Tsinghua University, China; Institute for Artificial Intelligence, China; Beijing National Research Center for Information Science and Technology, China; Beijing Academy of Artificial Intelligence, China; Corresponding author. Department of Computer Science and Technology, Tsinghua University, China

Journal volume & issue: Vol. 1
pp. 5 – 21

Abstract

Read online

Machine translation (MT) is an important sub-field of natural language processing that aims to translate natural languages using computers. In recent years, end-to-end neural machine translation (NMT) has achieved great success and has become the new mainstream method in practical MT systems. In this article, we first provide a broad review of the methods for NMT and focus on methods relating to architectures, decoding, and data augmentation. Then we summarize the resources and tools that are useful for researchers. Finally, we conclude with a discussion of possible future research directions.

Published in AI Open

ISSN: 2666-6510 (Online)
Publisher: KeAi Communications Co. Ltd.
Country of publisher: China
LCC subjects: Science: Mathematics: Instruments and machines: Electronic computers. Computer science
Website: https://www.keaipublishing.com/en/journals/ai-open/

About the journal

Abstract

Keywords