关系抽取
关系(数据库)
计算机科学
表(数据库)
联想(心理学)
信息抽取
接头(建筑物)
集合(抽象数据类型)
代表(政治)
编码(内存)
命名实体识别
自然语言处理
情报检索
序列(生物学)
词(群论)
数据挖掘
关联规则学习
鉴定(生物学)
人工智能
任务(项目管理)
语言学
哲学
经济
建筑工程
工程类
管理
认识论
政治
程序设计语言
法学
生物
植物
遗传学
政治学
作者
Cheng Cheng,Qingtian Zeng,Hua Zhao,Shansong Wang
标识
DOI:10.1177/01655515221144862
摘要
In this article, we propose a joint extraction of entity–relation triplets in natural disaster cases based on word pair relation table filling. For computational accuracy concerns or other reasons, traditional works often do entity recognition and relation extraction separately; it might put less attention over the task connections and triplet global association. We propose the Global Table Attention GRU (GL-TGRU) model as a joint approach that uses sequence information encoding and table information encoding to jointly learn the representation and enhance the global association of entity and relation in table filling. We evaluated the proposed model on the public data set SciERC and the natural disaster data set SSD-HDS, respectively. The F 1 scores of experimental results of the GL-TGRU model for entity identification and relation extraction achieved 65.81% and 37.30% on SciERC and achieved 93.89% and 84.06% on SSD-HDS. The results show our model helps to capture more global association relations of entity and relation, which can better identify the entity–relation triplet information.
科研通智能强力驱动
Strongly Powered by AbleSci AI