摘要
机器翻译是指通过计算机将源语言句子翻译到与之语义等价的目标语言句子的过程,是自然语言处理领域的一个重要研究方向。神经机器翻译仅需使用神经网络就能实现从源语言到目标语言的端到端翻译,目前已成为机器翻译研究的主流方向。该文选取了近期神经机器翻译的几个主要研究领域,包括同声传译、多模态机器翻译、非自回归模型、篇章翻译、领域自适应、多语言翻译和模型训练,并对这些领域的前沿研究进展做简要介绍。
Machine translation is a task which translates a source language into a target language of the equivalent meaning via a computer,which has become an important research direction in the field of natural language processing.Neural machine translation models,as the main stream in the reasearch community,can perform end-to-end translation from source language to target language.In this paper,we select several main research directions of neural machine translation,including model training,simultaneous translation,multi-modal translation,non-autoregressive translation,document-level translation,domain adaptation,multilingual translation,and briefly introduce the research progresses in these directions.
作者
冯洋
邵晨泽
FENG Yang;SHAO Chenze(Key Laboratory of Intelligent Information Processing,Institute of Computing Technology,Chinese Academy of Sciences,Beijing 100190,China;University of Chinese Academy of Sciences,Beijing 100049,China)
出处
《中文信息学报》
CSCD
北大核心
2020年第7期1-18,共18页
Journal of Chinese Information Processing
基金
国家重点研发计划政府间国际科技创新合作重点专项(2017YFE0192900)
关键词
神经机器翻译
模型训练
同声传译
多模态机器翻译
非自回归机器翻译
篇章翻译
领域自适应
多语言翻译
neural machine translation
model training
simultaneous translation
multi-modal translation
non-autoregressive translation
document-level translation
domain adaptation
multilingual translation
作者简介
冯洋(1982—),博士,副研究员,博士生导师,主要研究领域为机器翻译。E-mail:yangyang@ict.ac.cn;邵晨泽(1996—),博士研究生,主要研究领域为机器翻译。E-mail:shaochenze18z@ict.ac.cn
