《计算机应用》唯一官方网站 ›› 2023, Vol. 43 ›› Issue (2): 329-334.DOI: 10.11772/j.issn.1001-9081.2021122067

• 人工智能 •    下一篇

交互式机器翻译综述

廖兴滨1,2, 秦小林1,2(), 张思齐1,2, 钱杨舸1,2   

  1. 1.中国科学院 成都计算机应用研究所,成都 610213
    2.中国科学院大学 计算机科学与技术学院,北京 101408
  • 收稿日期:2021-12-09 修回日期:2022-05-03 接受日期:2022-06-10 发布日期:2022-06-30 出版日期:2023-02-10
  • 通讯作者: 秦小林
  • 作者简介:廖兴滨(1994—),男,湖北十堰人,硕士研究生,CCF会员,主要研究方向:自然语言处理、数据泄露预防
    秦小林(1980—),男,重庆人,研究员,博士生导师,博士,CCF会员,主要研究方向:人工智能、自动推理
    张思齐(1995—),男,安徽淮南人,博士研究生,主要研究方向:自然语言处理、时序逻辑
    钱杨舸(1997—),男,山东潍坊人,硕士研究生,主要研究方向:自然语言处理、人工智能。
  • 基金资助:
    四川省科技计划项目(2019ZDZX0006);中国科学院STS计划区域重点项目(A类)(KFJ?STS?QYZD?2021?21?001)

Review of interactive machine translation

Xingbin LIAO1,2, Xiaolin QIN1,2(), Siqi ZHANG1,2, Yangge QIAN1,2   

  1. 1.Chengdu Institute of Computer Applications,Chinese Academy of Sciences,Chengdu Sichuan 610213,China
    2.School of Computer Science and Technology,University of Chinese Academy of Sciences,Beijing 101408,China
  • Received:2021-12-09 Revised:2022-05-03 Accepted:2022-06-10 Online:2022-06-30 Published:2023-02-10
  • Contact: Xiaolin QIN
  • About author:LIAO Xingbin, born in 1994, M. S. candidate. His research interests include natural language processing, data leakage prevention.
    QIN Xiaolin, born in 1980, Ph. D., research fellow. His research interests include artificial intelligence, automated reasoning.
    ZHANG Siqi, born in 1995, Ph. D. candidate. His research interests include natural language processing, temporal logic.
    QIAN Yangge, born in 1997, M. S. candidate. His research interests include natural language processing, artificial intelligence.
  • Supported by:
    Sichuan Science and Technology Program(2019ZDZX0006);CAS STS Plan Regional Key Project (Class A)(KFJ?STS?QYZD?2021?21?001)

摘要:

随着深度学习的发展和成熟,神经机器翻译的质量也越来越高,然而仍不完美,为了达到可接受的翻译效果,需要人工进行后期编辑。交互式机器翻译(IMT)是这种串行工作的一个替代,即在翻译过程中进行人工互动,由用户对翻译系统产生的候选翻译进行验证,并且,如有必要,由用户提供新的输入,系统根据用户当前的反馈生成新的候选译文,如此往复,直到产生一个使用户满意的输出。首先,介绍了IMT的基本概念以及当前的研究进展;然后,分类对一些常用方法和前沿工作加以介绍,并简述每个工作的背景和创新之处;最后,探讨了IMT的发展趋势和研究难点。

关键词: 机器翻译, 交互式机器翻译, 交互式统计机器翻译, 交互式神经机器翻译, 强化学习, 自然语言处理

Abstract:

With the development and maturity of deep learning, the quality of neural machine translation has increased, yet it is still not perfect and requires human post-editing to achieve acceptable translation results. Interactive Machine Translation (IMT) is an alternative to this serial work, that is performing human interaction during the translation process, where the user verifies the candidate translations produced by the translation system and, if necessary, provides new input, and the system generates new candidate translations based on the current feedback of users, this process repeats until a satisfactory output is produced. Firstly, the basic concept and the current research progresses of IMT were introduced. Then, some common methods and state-of-the-art works were suggested in classification, while the background and innovation of each work were briefly described. Finally, the development trends and research difficulties of IMT were discussed.

Key words: machine translation, Interactive Machine Translation (IMT), Interactive Statistical Machine Translation (ISMT), Interactive Neural Machine Translation (INMT), Reinforcement Learning (RL), Natural Language Processing (NLP)

中图分类号: