摘要
神经机器翻译是近几年出现并快速发展的一种深度学习驱动的新型机器翻译模式,目前已成为机器翻译学术和工业界广为接受的主流技术.本文总结了我们在神经机器翻译方面的工作,特别是在各种信息和知识约束条件下提出的一系列神经机器翻译模型和方法,具体包括隐变量约束的变分神经机器翻译模型、单词与短语级统计机器翻译译文推荐与约束模型、源端句法结构约束模型.除此之外,本文也对神经机器翻译未来发展进行了初步思考和展望.
Neural machine translation（NMT）, powered by deep learning, is an emerging machine translation paradigm that has been advancing rapidly in recent years. It has become mainstream technology in both academia and industry of machine translation. This paper provides an overview of our research work on NMT. It particularly focuses on a series of NMT models proposed for considering a variety of useful information and knowledge constraints, which include variational NMT with constraints of latent variables, NMT advised by statistical machine translation, and NMT with syntactical constraints from the source language. In addition to this overview,this paper presents an outlook of the future trends in NMT.
作者
熊德意
李军辉
王星
张飚
Deyi XIONG;Junhui LI;Xing WANG;Biao ZHANG(School of Computer Science and Technology, Soochow University, Suzhou 215006. China;Software School, Xiarnen University, Xiamen 361005, China)
出处
《中国科学：信息科学》
CSCD
北大核心
2018年第5期574-588,共15页
Scientia Sinica(Informationis)
基金
国家自然科学基金优秀青年基金(批准号:61622209)资助项目
关键词
神经机器翻译
变分神经机器翻译
神经机器翻译与统计机器翻译融合
句法约束的神经机器翻译
neural machine translation
variational neural machine translation
fusion of neural and statistical machinc translation
ncural machine trauslation with syntactical constraints
