计算机与现代化 ›› 2021, Vol. 0 ›› Issue (07): 38-42.

• 算法设计与分析 • 上一篇    下一篇

基于ELMO的低资源神经机器翻译

  

  1. (1.东北石油大学计算机与信息技术学院,黑龙江大庆163318;
    2.哈尔滨工业大学计算机科学与技术学院,黑龙江哈尔滨150001)
  • 出版日期:2021-08-02 发布日期:2021-08-02
  • 作者简介:王浩畅(1974—),女,黑龙江大庆人,教授,博士后,研究方向:人工智能,自然语言处理,数据挖掘,生物信息学,E-mail: kinghaosing@gmail.com; 通信作者:孙孟冉(1994—),男,安徽滁州人,硕士研究生,研究方向:神经机器翻译,E-mail: sunmr@foxmail.com; 赵铁军(1962—),男,黑龙江哈尔滨人,教授,博士生导师,博士,研究方向:机器翻译,自然语言处理,E-mail: tjzhao@hit.edu.cn。
  • 基金资助:
    国家自然科学基金资助项目(61402099, 61702093)

Low-resource Neural Machine Translation Based on ELMO

  1. (1. School of Computer and Information Technology, Northeast Petroleum University, Daqing 163318, China;
    2. School of Computer Science and Technology, Harbin Institute of Technology, Harbin 150001, China)
  • Online:2021-08-02 Published:2021-08-02

摘要: 低资源神经机器翻译的研究难点是缺乏大量的平行语料来给模型进行训练。随着预训练模型的发展,并且在各大自然语言处理任务中均取得很大的提升,本文提出一种融合ELMO预训练模型的神经机器翻译模型来解决低资源神经机器翻译问题。本文模型在土耳其语-英语低资源翻译任务上相比于反向翻译提升超过0.7个BLEU,在罗马尼亚语-英语翻译任务上提升超过0.8个BLEU。此外,在模拟的中-英、法-英、德-英、西-英这4组低资源翻译任务上相比于传统神经机器翻译模型分别提升2.3、3.2、2.6、3.2个BLEU。实验表明使用融合ELMO的模型来解决低资源神经机器翻译问题是有效的。

关键词: 低资源, 平行语料, 预训练模型, 神经机器, 翻译模型

Abstract: The difficulty in low-resource neural machine translation is lack of numerous parallel corpus to train the model. With the development of the pre-training model, it has made great improvements in various natural language processing tasks. In this paper, a neural machine translation model combining ELMO is proposed to solve the problem of low-resource neural machine translation. There are more than 0.7 BLEU improvements in the Turkish-English low-resource translation task compared to the back translation, and more than 0.8 BLEU improvements in the Romanian-English translation task. In addition, compared with the traditional neural machine translation model, the simulated low-resource translation tasks of Chinese-English, French-English, German-English and Spanish-English increase by 2.3, 3.2, 2.6 and 3.2 BLEU respectively. The experimental results show that the ELMO model is effective for low-resource neural machine translation.

Key words: low-resource, parallel corpus, pre-training model, neural machine, translation model