摘要
探索将XLM-R跨语种预训练语言模型应用在神经机器翻译的源语言端、目标语言端和两端,提高机器翻译的质量。提出3种网络模型,分别在Transformer神经网络模型的编码器、解码器以及两端同时引入预训练的XLM-R多语种词语表示。在WMT英语-德语、IWSLT英语-葡萄牙语以及英语-越南语等翻译中的实验结果表明,对双语平行语料资源丰富的翻译任务,引入XLM-R可以很好地对源语言句子进行编码,从而提高翻译质量;对双语平行语料资源匮乏的翻译任务,引入XLM-R不仅可以很好地对源语言句子进行编码,还可以对源语言端和目标语言端的知识同时进行补充,提高翻译质量。
The authors explore the application of XLM-R cross-lingual pre-training language model into the source language,into the target language and into both of them to improve the quality of machine translation,and propose three neural network models,which integrate pre-trained XLM-R multilingual word representation into the Transformer encoder,into the Transformer decoder and into both of them respectively.The experimental results on WMT English-German,IWSLT English-Portuguese and English-Vietnamese machine translation benchmarks show that integrating XLM-R model into Transformer encoder can effectively encode the source sentences and improve the system performance for resource-rich translation task.For resource-poor translation task,integrating XLM-R model can not only encode the source sentences well,but also supplement the source language knowledge and target language knowledge at the same time,thus improve the translation quality.
作者
王倩
李茂西
吴水秀
王明文
WANG Qian;LI Maoxi;WU Shuixiu;WANG Mingwen(School of Computer and Information Engineering,Jiangxi Normal University,Nanchang 330022)
出处
《北京大学学报(自然科学版)》
EI
CAS
CSCD
北大核心
2022年第1期29-36,共8页
Acta Scientiarum Naturalium Universitatis Pekinensis
基金
国家自然科学基金(61662031)资助。