Neural Machine Translation: Challenges, Progress and Future

2020/04/13 by Jiajun Zhang, Chengqing Zong, Zhang, Jiajun +1 · 2 citations
Computer Science · #Computation and Language (cs.CL) #FOS: Computer and information sciences #cs.CL

paper · pdf · doi:10.48550/arxiv.2004.05809

Invited Review of Science China Technological Sciences

arxiv created 2020/04/13 · arxiv updated 2020/04/14

Abstract

Machine translation (MT) is a technique that leverages computers to translate human languages automatically. Nowadays, neural machine translation (NMT) which models direct mapping between source and target languages with deep neural networks has achieved a big breakthrough in translation performance and become the de facto paradigm of MT. This article makes a review of NMT framework, discusses the challenges in NMT, introduces some exciting recent progresses and finally looks forward to some potential future research trends. In addition, we maintain the state-of-the-art methods for various NMT tasks at the website https://github.com/ZNLP/SOTA-MT.

Cited by

• NSL-MT: Linguistically Informed Negative Samples for Efficient Machine Translation in Low-Resource Languages
• Bridging Language Gaps with Adaptive RAG: Improving Indonesian Language Question Answering

Related

• Neural Machine Translation: A Review of Methods, Resources, and Tools
• Neural Machine Translation: A Review and Survey
• A Survey of Deep Learning Techniques for Neural Machine Translation
• Machine Translation : From Statistical to modern Deep-learning practices
• A Comprehensive Survey of Multilingual Neural Machine Translation