基于中文信息与越南语句法指导的越南语事件检测(Vietnamese event detection based on Chinese information and Vietnamese syntax guidance)

Long Chen (陈龙), Junjun Guo (郭军军), Yafei Zhang (张亚飞), Chengxiang Gao (高盛祥), Zhengtao Yu (余正涛)


Abstract
当前基于深度学习的事件检测模型都依赖足够数量的标注数据,而标注数据的稀缺及事件类型歧义为越南语事件检测带来了极大的挑战。根据“表达相同观点但语言不同的句子通常有相同或相似的语义成分”这一多语言一致性特征,本文提出了一种基于中文信息与越南语句法指导的越南语事件检测框架。首先通过共享编码器策略和交叉注意力网络将中文信息融入到越南语中,然后使用图卷积网络融入越南语依存句法信息,最后在中文事件类型指导下实现越南语事件检测。实验结果表明,在中文信息和越南语句法的指导下越南语事件检测取得了较好的效果。
Anthology ID:
2021.ccl-1.14
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:
143–155
Language:
Chinese
URL:
https://aclanthology.org/2021.ccl-1.14
DOI:
Bibkey:
Cite (ACL):
Long Chen, Junjun Guo, Yafei Zhang, Chengxiang Gao, and Zhengtao Yu. 2021. 基于中文信息与越南语句法指导的越南语事件检测(Vietnamese event detection based on Chinese information and Vietnamese syntax guidance). In Proceedings of the 20th Chinese National Conference on Computational Linguistics, pages 143–155, Huhhot, China. Chinese Information Processing Society of China.
Cite (Informal):
基于中文信息与越南语句法指导的越南语事件检测(Vietnamese event detection based on Chinese information and Vietnamese syntax guidance) (Chen et al., CCL 2021)
Copy Citation:
PDF:
https://preview.aclanthology.org/ingestion-script-update/2021.ccl-1.14.pdf