面向法律文本的实体关系联合抽取算法(Joint Entity and Relation Extraction for Legal Texts)

Wenhui Song (宋文辉), Xiang Zhou (周翔), Ping Yang (杨萍), Yuanyuan Sun (孙媛媛), Liang Yang (杨亮), Hongfei Lin (林鸿飞)


Abstract
法律文本中包含的丰富信息可以通过结构化的实体关系三元组进行表示,便于法律知识的存储和查询。传统的流水线方法在自动抽取三元组时执行了大量冗余计算,造成了误差传播。而现有的联合学习方法无法适用于有大量重叠关系的法律文本,也并未关注语法结构信息对文本表示的增强,因此本文提出一种面向法律文本的实体关系联合抽取模型。该模型首先通过ON-LSTM注入语法信息,然后引入多头注意力机制分解重叠关系。相较于流水线和其他联合学习方法本文模型抽取效果最佳,在涉毒类法律文本数据集上抽取结果的F1值达到78.7%。
Anthology ID:
2021.ccl-1.53
Volume:
Proceedings of the 20th Chinese National Conference on Computational Linguistics
Month:
August
Year:
2021
Address:
Huhhot, China
Editors:
Sheng Li (李生), Maosong Sun (孙茂松), Yang Liu (刘洋), Hua Wu (吴华), Kang Liu (刘康), Wanxiang Che (车万翔), Shizhu He (何世柱), Gaoqi Rao (饶高琦)
Venue:
CCL
SIG:
Publisher:
Chinese Information Processing Society of China
Note:
Pages:
589–599
Language:
Chinese
URL:
https://aclanthology.org/2021.ccl-1.53
DOI:
Bibkey:
Cite (ACL):
Wenhui Song, Xiang Zhou, Ping Yang, Yuanyuan Sun, Liang Yang, and Hongfei Lin. 2021. 面向法律文本的实体关系联合抽取算法(Joint Entity and Relation Extraction for Legal Texts). In Proceedings of the 20th Chinese National Conference on Computational Linguistics, pages 589–599, Huhhot, China. Chinese Information Processing Society of China.
Cite (Informal):
面向法律文本的实体关系联合抽取算法(Joint Entity and Relation Extraction for Legal Texts) (Song et al., CCL 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.ccl-1.53.pdf