Neural Machine Translation: A Review of Methods, Resources, and Tools

Abstract

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.

Accepted by AI Open

References in corpus (15)

• PyTorch: An Imperative Style, High-Performance Deep Learning Library
• Sequence to Sequence Learning with Neural Networks
• Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation
• Cross-lingual Language Model Pretraining
• Dual Learning for Machine Translation
• Neural Machine Translation in Linear Time
• Word Translation Without Parallel Data
• Depthwise Separable Convolutions for Neural Machine Translation
• Insertion Transformer: Flexible Sequence Generation via Insertion Operations
• Is Neural Machine Translation Ready for Deployment? A Case Study on 30 Translation Directions
• THUMT: An Open Source Toolkit for Neural Machine Translation
• Are Transformers universal approximators of sequence-to-sequence functions?
• Pre-trained Language Model Representations for Language Generation
• Improving Sequence-to-Sequence Learning via Optimal Transport
• Neural Machine Translation: Challenges, Progress and Future