基于跨语种预训练语言模型XLM-R的神经机器翻译方法

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...

Neural Machine Translation Based on XLM-R Cross-lingualPre-training Language Model

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.