北京大学学报自然科学版 ›› 2023, Vol. 59 ›› Issue (1): 1-10.DOI: 10.13209/j.0479-8023.2022.063

上一篇    下一篇

基于单词领域特征敏感的多领域神经机器翻译

黄增城, 满志博, 张玉洁, 徐金安, 陈钰枫   

  1. 北京交通大学计算机与信息技术学院, 北京 100044
  • 收稿日期:2022-05-13 修回日期:2022-07-29 出版日期:2023-01-20 发布日期:2023-01-20
  • 通讯作者: 张玉洁, E-mail: yjzhang(at)bjtu.edu.cn
  • 基金资助:
    国家自然科学基金(61876198, 61976016 和 61976015)资助 

Word-Based Domain Feature-Sensitive Multi-domain Neural Machine Translation

HUANG Zengcheng, MAN Zhibo, ZHANG Yujie, XU Jin’an, CHEN Yufeng   

  1. School of Computer and Information Technology, Beijing Jiaotong University, Beijing 100044
  • Received:2022-05-13 Revised:2022-07-29 Online:2023-01-20 Published:2023-01-20
  • Contact: ZHANG Yujie, E-mail: yjzhang(at)bjtu.edu.cn

摘要:

鉴于现有基于单词的领域特征学习方法在领域识别上的精度较低, 为提高领域判别和提供准确的翻译, 提出一种单词级别的领域特征敏感学习机制, 包括两方面: 1) 编码器端的上下文特征编码, 为了扩展单词级别的领域特征学习范围, 引入卷积神经网络, 并行提取不同大小窗口的词串作为单词的上下文特征; 2) 强化的领域特征学习, 设计基于多层感知机的领域判别器模块, 增强从单词上下文特征中获取更准确领域比例的学习能力, 提升单词的领域判别准确率。在多领域UM-Corpus英–汉和OPUS英–法翻译任务中的实验结果显示, 所提方法平均BLEU值分别超过强基线模型0.82和1.06, 单词的领域判别准确率比基线模型分别提升10.07%和18.06%。对实验结果的进一步分析表明, 所提翻译模型性能的提升得益于所提出的单词领域特征敏感的学习机制。

关键词: 多领域神经机器翻译, 领域特征敏感, 上下文特征, 领域判别

Abstract:

The accuracy of the existing word-based domain feature learning methods on domain discrimination is still low and the further research for domain feature learning is required. In order to improve domain discrimination and provide accurate translation, this paper proposes a word-based domain feature-sensitive learning mechanism, including 1) the context feature encoding at encoder side, to widen the study range of word-based domain features, introducing convolutional neural networks (CNN) in encoder for extracting features from word strings with different lengths in parallel as word context features; and 2) enhanced domain feature learning. A domain discriminator module based on multi-layer perceptions (MLP) is designed to enhance the learning ability of obtaining more accurate domain proportion from word context features and improve the accuracy of word domain discrimination. Experiments on English-Chinese task of UM-Corpus and English-French task of OPUS show that the average BLEU scores of the proposed method exceed the strong baseline by 0.82 and 1.06 respectively. The accuracy of domain discrimination is improved by 10.07% and 18.06% compared with the baseline. More studies illustrate that the improvements of average BLEU scores and accuracy of domain discrimation are contributed by the proposed word-based domain feature-sensitive learning mechanism.

Key words: multi-domain NMT, domain feature-sensitive, context features, domain discrimination