ISSN 1000-1239 CN 11-1777/TP

计算机研究与发展 ›› 2017, Vol. 54 ›› Issue (6): 1144-1149.doi: 10.7544/issn1000-1239.2017.20160805

所属专题: 2017优青专题

• 综述 • 上一篇    下一篇

神经机器翻译前沿进展

刘洋   

  1. (清华大学计算机科学与技术系 北京 100084) (清华信息科学与技术国家实验室(筹) 北京 100084) (智能技术与系统国家重点实验室(清华大学) 北京 100084) (liuyang2011@tsinghua.edu.cn)
  • 出版日期: 2017-06-01
  • 基金资助: 
    国家自然科学基金优秀青年科学基金项目(61522204)

Recent Advances in Neural Machine Translation

Liu Yang   

  1. (Department of Computer Science and Technology, Tsinghua University, Beijing 100084) (Tsinghua National Laboratory for Information Science and Technology, Beijing 100084) (State Key Laboratory of Intelligent Technology and Systems (Tsinghua University), Beijing 100084)
  • Online: 2017-06-01

摘要: 机器翻译研究如何利用计算机实现自然语言之间的自动翻译,是人工智能和自然语言处理领域的重要研究方向之一.近年来,基于深度学习的神经机器翻译方法获得迅速发展,目前已取代传统的统计机器翻译成为学术界和工业界新的主流方法.首先介绍神经机器翻译的基本思想和主要方法,然后对最新的前沿进展进行综述,最后对神经机器翻译的未来发展方向进行展望.

关键词: 人工智能, 深度学习, 神经机器翻译, 编码器-解码器架构, 注意力机制

Abstract: Machine translation, which aims at automatically translating between natural languages using computers, is one of important research directions in artificial intelligence and natural language processing. Recent years have witnessed the rapid development of neural machine translation, which has replaced conventional statistical machine translation to become the new mainstream technique in both academia and industry. This paper first introduces the basic ideas and state-of-the-art approaches in neural machine translation and then reviews recent important research findings. The paper concludes with a discussion about possible future directions.

Key words: artificial intelligence, deep learning, neural machine translation, encoder-decoder framework, attention mechanism

中图分类号: