基于提高伪平行句对质量的无监督领域适应机器翻译  

Unsupervised domain-adapted machine translation based on improving the quality of pseudo-parallel sentence pairs

作　　者：肖妮妮 金畅 段湘煜 XIAO Ni-ni;JIN Chang;DUAN Xiang-yu(Natural Language Processing Laboratory,School of Computer Science and Technology,Soochow University,Suzhou 215006,China)

机构地区：[1]苏州大学计算机科学与技术学院自然语言处理实验室,江苏苏州215006

出　　处：《计算机工程与科学》2022年第12期2230-2237,共8页Computer Engineering & Science

摘　　要：神经机器翻译系统的良好性能依赖于大规模内领域双语平行数据,当特定领域数据稀疏或不存在时,领域适应是个很好的解决办法。无监督领域适应方法通过构建伪平行语料来微调预训练的翻译模型,然而现有的方法没有充分考虑语言的语义、情感等特性,导致目标领域的翻译包含大量的错误和噪声,从而影响到模型的跨领域性能。为缓解这一问题,从模型和数据2个方面来提高伪平行句对的质量,以提高模型的领域自适应能力。首先,提出更加合理的预训练策略来学习外领域数据更为通用的文本表示,增强模型的泛化能力,同时提高内领域的译文准确性;然后,融合句子的情感信息进行后验筛选,进一步改善伪语料的质量。实验表明,该方法在中-英与英-中实验上比强基线系统反向翻译的BLEU值分别提高了1.25和1.38,可以有效地提高翻译效果。The good performance of neural machine translation system depends on a large amount of in-domain bilingual parallel data.Domain adaptation is a good solution when the specific domain data is sparse or non-existent.Unsupervised domain adaptation strategies fine-tune the pre-trained translation models by generating pseudo-parallel corpus.However,existing methods do not consider the semantic and emotional characteristics of the languages sufficiently,resulting in a lot of errors and noises in the target domain translation,which affects the cross-domain performance of the model.To alleviate this problem,this paper improves the quality of pseudo-parallel sentence pairs by combining model and data,so as to improve the adaptive ability of the model domain.Firstly,a more reasonable pre-training strategy is proposed to learn more general textual representations of out-domain data,in order to enhance the generalization capability of the model and improve the accuracy of the generated in-domain pseudocorpus.Then,sentence sentiment features are combined to do posteriori filtering,in order to improve the quality of pseudo-parallel corpus.The experimental results show that,compared with the strong baseline system with back-translation,this method increases the BLEU value by 1.25 and 1.38 respectively in the Chinese-English and English-Chinese translation experiments,thus effectively improving the translation performance.

关 键 词：神经网络 神经机器翻译 领域适应 模型优化 情感信息 

分 类 号：H085[语言文字—语言学]