GSM-EL: A Generalizable Symbol-Manipulation Approach for Entity Linking

doi:10.1109/TKDE.2024.3523399

	GSM-EL: A Generalizable Symbol-Manipulation Approach for Entity Linking
	Cheng, Xueqi 1,2; Wang, Yuanzheng 1,2; Fan, Yixing 1,2; Guo, Jiafeng 1,2; Zhang, Ruqing 1,2; Bi, Keping 1,2
	2025-03-01
发表期刊	IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING
ISSN	1041-4347
卷号	37 期号:3 页码:1213-1226
摘要	Entity linking (EL) is a challenging task as it typically requires matching an ambiguous entity mention with its corresponding entity in a knowledge base (KB). The mainstream studies focus on learning and evaluating linking models on the same corpus and obtained significant performance achievement, however, they often overlook the generalization ability to out-of-domain corpus, which is more realistic yet much more challenging. To address this issue, we introduce a novel neural-symbolic model for entity linking, which is inspired by the symbol-manipulation mechanism in human brains. Specifically, we abstract diverse features into unified variables, then combine them using neural operators to capture diverse relevance requirements, and finally aggregate relevance scores through voting. We conduct experiments on eleven benchmark datasets with different types of text, and the results show that our method outperforms nearly all baselines. Notably, the best performance of our method on seven out-of-domain datasets highlights its generalization ability.
关键词	Neural networks Biological neural networks Feature extraction Adaptation models Training Liquids Knowledge engineering Knowledge based systems Hands Vectors Neural-symbolic method symbol-manipulation entity linking
DOI	10.1109/TKDE.2024.3523399
收录类别	SCI
语种	英语
资助项目	National Natural Science Foundation of China (NSFC)[62372431] ; National Natural Science Foundation of China (NSFC)[62472408] ; National Natural Science Foundation of China (NSFC)[62302486] ; Strategic Priority Research Program of the CAS[XDB0680102] ; Youth Innovation Promotion Association CAS[2021100] ; Lenovo-CAS Joint Lab Youth Scientist Project[JCKY2022130C039] ; National Key Research and Development Program of China[2023YFA1011602] ; Innovation Project of ICT CAS[E361140] ; CAS Special Research Assistant Funding Project
WOS研究方向	Computer Science ; Engineering
WOS类目	Computer Science, Artificial Intelligence ; Computer Science, Information Systems ; Engineering, Electrical & Electronic
WOS记录号	WOS:001410873400010
出版者	IEEE COMPUTER SOC
引用统计
文献类型	期刊论文
条目标识符	http://119.78.100.204/handle/2XEOYT63/40769
专题	中国科学院计算技术研究所期刊论文_英文
通讯作者	Fan, Yixing
作者单位	1.Univ Chinese Acad Sci, Sch Comp Sci & Technol, Beijing 100049, Peoples R China 2.Chinese Acad Sci, Inst Comp Technol, CAS Key Lab Network Data Sci & Technol, Beijing 100864, Peoples R China
推荐引用方式 GB/T 7714	Cheng, Xueqi,Wang, Yuanzheng,Fan, Yixing,et al. GSM-EL: A Generalizable Symbol-Manipulation Approach for Entity Linking[J]. IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING,2025,37(3):1213-1226.
APA	Cheng, Xueqi,Wang, Yuanzheng,Fan, Yixing,Guo, Jiafeng,Zhang, Ruqing,&Bi, Keping.(2025).GSM-EL: A Generalizable Symbol-Manipulation Approach for Entity Linking.IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING,37(3),1213-1226.
MLA	Cheng, Xueqi,et al."GSM-EL: A Generalizable Symbol-Manipulation Approach for Entity Linking".IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING 37.3(2025):1213-1226.