Computer Engineering and Applications ›› 2022, Vol. 58 ›› Issue (16): 49-55.DOI: 10.3778/j.issn.1002-8331.2201-0227

• Research Hotspots and Reviews • Previous Articles     Next Articles

Survey of Pivot Methods for Neural Machine Translation

LI Jiaquan, WANG Liqing, LI Peng, JIANG Xiaomin, XU Yongyue   

  1. 1.School of Information Science & Engineering, Yunnan University, Kunming 650091, China
    2.Yunnan Media Group, Kunming 650500, China
  • Online:2022-08-15 Published:2022-08-15

面向神经机器翻译的枢轴方法研究综述

黎家全,王丽清,李鹏,蒋晓敏,徐永跃   

  1. 1.云南大学 信息学院,昆明 650091
    2.云南广播电视台,昆明 650500

Abstract: Neural machine translation(NMT)for low-resource languages has always been a difficult and hot research topic in the field of machine translation, and pivot-based methods provide ideas for improving its performance. Aiming at the application of the pivot idea in low-resource NMT, this paper divides the research into three aspects:pivot translation, pivot-based pseudo-parallel data generation and pivot-based model construction, then analyzes and compares the research status at home and abroad, main problems and trends of different methods, which can provide a reference for the research in this field.

Key words: pivot methods, neural machine translation(NMT), low-resource machine translation

摘要: 低资源语言的神经机器翻译(neural machine translation,NMT)一直是机器翻译领域研究的难点和热点,基于枢轴的方法为其性能的提升和改进提供了思路。针对枢轴思想在低资源语言神经机器翻译中的应用,从枢轴翻译、基于枢轴的伪平行数据生成和基于枢轴的模型构建三方面,对不同方法的国内外研究现状、主要问题和趋势进行了分析和比较,为该领域的研究提供参考和借鉴。

关键词: 枢轴方法, 神经机器翻译(NMT), 低资源机器翻译