Abstract
神经机器翻译在低资源语言的翻译任务中存在翻译难度大、译文质量不佳的问题。本文针对低资源语言与汉语之间没有双语平行语料的情况,采用正反向枢轴翻译的方法,生成了三种低资源语言到汉语的平行句对,采用词汇级的系统融合技术,将Transformer模型和对偶学习模型翻译生成的目标语言译文进行融合,然后通过混淆神经网络进行词汇选择,生成了更为优质的目标语言译文。实验证明,本文提出的多模型融合方法在爱沙尼亚语-汉语、拉脱维亚语-汉语、罗马尼亚语-汉语这三种低资源语言翻译任务中均优于独立模型的翻译效果,进一步提升了低资源语言神经机器翻译的译文质量。- Anthology ID:
- 2021.ccl-1.5
- Volume:
- Proceedings of the 20th Chinese National Conference on Computational Linguistics
- Month:
- August
- Year:
- 2021
- Address:
- Huhhot, China
- Venue:
- CCL
- SIG:
- Publisher:
- Chinese Information Processing Society of China
- Note:
- Pages:
- 46–56
- Language:
- Chinese
- URL:
- https://aclanthology.org/2021.ccl-1.5
- DOI:
- Cite (ACL):
- Xiaobing Zhao, Bo Jin, and Yuan Sun. 2021. 基于枢轴语言系统融合的词汇混淆网络神经机器翻译(Neural Machine Translation for Vocabulary Confusion Network Based on Pivotal Language System Fusion). In Proceedings of the 20th Chinese National Conference on Computational Linguistics, pages 46–56, Huhhot, China. Chinese Information Processing Society of China.
- Cite (Informal):
- 基于枢轴语言系统融合的词汇混淆网络神经机器翻译(Neural Machine Translation for Vocabulary Confusion Network Based on Pivotal Language System Fusion) (Zhao et al., CCL 2021)
- PDF:
- https://preview.aclanthology.org/ingestion-script-update/2021.ccl-1.5.pdf