基于BERT的端到端中文篇章事件抽取(A BERT-based End-to-End Model for Chinese Document-level Event Extraction)

Hongkuan Zhang (张洪宽), Hui Song (宋晖), Shuyi Wang (王舒怡), Bo Xu (徐波)


Abstract
篇章级事件抽取研究从整篇文档中检测事件,识别出事件包含的元素并赋予每个元素特定的角色。本文针对限定领域的中文文档提出了基于BERT的端到端模型,在模型的元素和角色识别中依次引入前序层输出的事件类型以及实体嵌入表示,增强文本的事件、元素和角色关联表示,提高篇章中各事件所属元素的识别精度。在此基础上利用标题信息和事件五元组的嵌入式表示,实现主从事件的划分及元素融合。实验证明本文的方法与现有工作相比具有明显的提升。
Anthology ID:
2020.ccl-1.36
Volume:
Proceedings of the 19th Chinese National Conference on Computational Linguistics
Month:
October
Year:
2020
Address:
Haikou, China
Editors:
Maosong Sun (孙茂松), Sujian Li (李素建), Yue Zhang (张岳), Yang Liu (刘洋)
Venue:
CCL
SIG:
Publisher:
Chinese Information Processing Society of China
Note:
Pages:
390–401
Language:
Chinese
URL:
https://aclanthology.org/2020.ccl-1.36
DOI:
Bibkey:
Cite (ACL):
Hongkuan Zhang, Hui Song, Shuyi Wang, and Bo Xu. 2020. 基于BERT的端到端中文篇章事件抽取(A BERT-based End-to-End Model for Chinese Document-level Event Extraction). In Proceedings of the 19th Chinese National Conference on Computational Linguistics, pages 390–401, Haikou, China. Chinese Information Processing Society of China.
Cite (Informal):
基于BERT的端到端中文篇章事件抽取(A BERT-based End-to-End Model for Chinese Document-level Event Extraction) (Zhang et al., CCL 2020)
Copy Citation:
PDF:
https://preview.aclanthology.org/improve-issue-templates/2020.ccl-1.36.pdf