Abstract
在汉语等其他有省略代词习惯的语言中,通常会删掉可从上下文信息推断出的代词。尽管以Transformer为代表的的神经机器翻译模型取得了巨大的成功,但这种省略现象依旧对神经机器翻译模型造成了很大的挑战。本文在Transformer基础上提出了一个融合零指代识别的翻译模型,并引入篇章上下文来丰富指代信息。具体地,该模型采用联合学习的框架,在翻译模型基础上,联合了一个分类任务,即判别句子中省略代词在句子所表示的成分,使得模型能够融合零指代信息辅助翻译。通过在中英对话数据集上的实验,验证了本文提出方法的有效性,与基准模型相比,翻译性能提升了1.48个BLEU值。- Anthology ID:
- 2021.ccl-1.1
- 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:
- 1–12
- Language:
- Chinese
- URL:
- https://aclanthology.org/2021.ccl-1.1
- DOI:
- Cite (ACL):
- Hao Wang, Junhui Li, and Zhengxian Gong. 2021. 融合零指代识别的篇章级机器翻译(Context-aware Machine Translation Integrating Zero Pronoun Recognition). In Proceedings of the 20th Chinese National Conference on Computational Linguistics, pages 1–12, Huhhot, China. Chinese Information Processing Society of China.
- Cite (Informal):
- 融合零指代识别的篇章级机器翻译(Context-aware Machine Translation Integrating Zero Pronoun Recognition) (Wang et al., CCL 2021)
- PDF:
- https://preview.aclanthology.org/auto-file-uploads/2021.ccl-1.1.pdf