Research on Entity Linking Method Based on Contrastive Learning and Re-ranking

doi:10.19678/j.issn.1000-3428.0070629

Computer Engineering ›› 2026, Vol. 52 ›› Issue (9): 123-132. doi: 10.19678/j.issn.1000-3428.0070629

• Computational Intelligence and Pattern Recognition • Previous Articles Next Articles

Research on Entity Linking Method Based on Contrastive Learning and Re-ranking

LIU Junping¹^,²^,³, WANG Runpeng¹, HU Xinrong¹, PENG Tao¹, WANG Bangchao¹, YANG Huali¹, ZHU Qiang¹^,*()

1. School of Computer Science and Artificial Intelligence, Wuhan Textile University, Wuhan 430200, Hubei, China
2. Engineering Research Center of Hubei Province for Clothing Information, Wuhan 430200, Hubei, China
3. Hubei Provincial Research Center for Intelligent Textile and Fashion, Wuhan 430200, Hubei, China

Received:2024-11-19 Revised:2025-02-20 Online:2026-09-15 Published:2025-04-09
Contact: ZHU Qiang

基于对比学习和重排序的实体链接方法研究

刘军平¹^,²^,³, 王润鹏¹, 胡新荣¹, 彭涛¹, 王帮超¹, 杨华利¹, 朱强¹^,*()

1. 武汉纺织大学计算机与人工智能学院, 湖北武汉 430200
2. 湖北省服装信息化工程技术研究中心, 湖北武汉 430200
3. 纺织服装智能化湖北省工程研究中心, 湖北武汉 430200

通讯作者: 朱强
作者简介:
刘军平(CCF高级会员), 男, 副教授, 主研方向为自然语言处理、信息检索、知识图谱
王润鹏, 硕士研究生
胡新荣, 教授
彭涛, 教授
王帮超, 讲师
杨华利, 讲师
朱强(通信作者), 讲师
基金资助:
教育部人文社会科学研究一般项目(23YJAZH082); 湖北省教育科学规划重点课题(2022GA046); 国家自然科学基金青年科学基金项目(62102291); 湖北省自然科学基金计划项目(2024AFB736)

Abstract

Abstract:

Entity Linking (EL), which links entity mentions in natural text to corresponding entities within a knowledge base, plays a crucial role in fields such as information retrieval and question-answering systems. The key challenge in EL lies in the effective utilization of the contextual information of mentions and feature information of entities in the knowledge base to generate candidate entities and select the correct entity among them. Although some methods generate relevant candidate entities by relying on specific strategies and select appropriate entities by combining feature information, they often fail to capture deeper semantic relationships, resulting in an inability to obtain high-quality candidate entities. In some cases, the correct entity may not be included among the candidate entities. Meanwhile, in specific domains, limited entity information may impair the capability of some methods for multi-level interaction. To address these issues, this paper proposes a two-stage EL method. This method first generates high-quality candidate entities and then aggregates entity feature information to achieve re-ranking at both coarse- and fine-grained levels. Specifically, it retrieves high-quality candidate entities using a contrastive learning method based on hybrid negative sample sampling. Subsequently, it predicts the fine-grained entity types in a weakly supervised manner and uses both coarse- and fine-grained type information to re-rank the candidate entities. Experimental results on three public datasets demonstrate the effectiveness of this method in enhancing EL performance.

Key words: Entity Linking (EL), candidate entity generation, contrastive learning, mixed negative sampling, fine-grained entity types

摘要：

实体链接(EL)是一项将自然文本中的实体提及链接到知识库中相应实体的任务, 在信息检索、问答系统等领域发挥着重要作用。EL的挑战在于如何利用提及的上下文和知识库中实体的特征信息, 生成候选实体并选择其中正确的实体。尽管一些方法依靠某种策略生成了相关的候选实体, 并结合特征信息选择了合适的实体, 但是这些方法往往未能学习更深层次的语义信息, 导致不能得到高质量的候选实体, 甚至正确的实体不包含在候选实体中。同时, 在一些特定领域, 实体信息资源会出现不充分的情况, 使得一些方法缺乏在多个层面上进行交互的能力。为了解决以上问题, 提出一种两阶段的EL方法, 首先生成高质量的候选实体, 随后聚合实体特征信息以实现粗粒度和细粒度层面的重排序。具体地, 使用基于混合负样本采样的对比学习方法检索得到高质量的候选实体, 然后利用弱监督的方式预测实体细粒度的类型, 并使用粗粒度和细粒度的类型信息对候选实体进行重排序。在3个公共数据集上的实验结果表明, 该方法可以有效提升EL的效果。

关键词: 实体链接, 候选实体生成, 对比学习, 混合负样本采样, 细粒度实体类型

LIU Junping, WANG Runpeng, HU Xinrong, PENG Tao, WANG Bangchao, YANG Huali, ZHU Qiang. Research on Entity Linking Method Based on Contrastive Learning and Re-ranking[J]. Computer Engineering, 2026, 52(9): 123-132.

刘军平, 王润鹏, 胡新荣, 彭涛, 王帮超, 杨华利, 朱强. 基于对比学习和重排序的实体链接方法研究[J]. 计算机工程, 2026, 52(9): 123-132.

/ Recommend / Download Citations

URL: https://www.ecice06.com/EN/10.19678/j.issn.1000-3428.0070629

https://www.ecice06.com/EN/Y2026/V52/I9/123

Figures/Tables 12

Fig.1 The overall structure of the method in this paper

Fig.2 Recall@k results on the NCBI Disease dataset

Fig.3 Recall@k results on the MM(st21pv) dataset

Fig.4 Zero-shot entity linking results on MM(st21pv)

References 36

1	SUNG M, JEON H, LEE J, et al. Biomedical entity representations with synonym marginalization[EB/OL]. [2024-10-05]. https://arxiv.org/abs/2005.00239.
2	MURTY S, VERGA P, VILNIS L, et al. Hierarchical losses and new resources for fine-grained entity typing and linking[C]//Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics. [S. l. ]: ACL, 2018: 97-109.
3	CHEN L H , VAROQUAUX G , SUCHANEK F M . A lightweight neural model for biomedical entity linking. Proceedings of the AAAI Conference on Artificial Intelligence, 2021, 35 (14): 12657- 12665. doi: 10.1609/aaai.v35i14.17499
4	BODENREIDER O . The Unified Medical Language System (UMLS): integrating biomedical terminology. Nucleic Acids Research, 2004, 32 (9): 267- 270.
5	JESSOP D M , ADAMS S E , WILLIGHAGEN E L , et al. OSCAR4: a flexible architecture for chemical text-mining. Journal of Cheminformatics, 2011, 3 (1): 41. doi: 10.1186/1758-2946-3-41
6	ARONSON A R , LANG F M . An overview of METAMAP: historical perspective and recent advances. Journal of the American Medical Informatics Association, 2010, 17 (3): 229- 236. doi: 10.1136/jamia.2009.002733
7	LEAMAN R , ISLAMAJ D R , LU Z Y . DNorm: disease name normalization with pairwise learning to rank. Bioinformatics, 2013, 29 (22): 2909- 2917. doi: 10.1093/bioinformatics/btt474
8	LEAMAN R , LU Z Y . TaggerOne: joint named entity recognition and normalization with semi-Markov models. Bioinformatics, 2016, 32 (18): 2839- 2846. doi: 10.1093/bioinformatics/btw343
9	BHATTA J , SHRESTHA D , NEPAL S , et al. Efficient estimation of Nepali word representations in vector space. Journal of Innovations in Engineering Education, 2021, 3 (1): 71- 77.
10	NIU J H , YANG Y H , ZHANG S H , et al. Multi-task character-level attentional networks for medical concept normalization. Neural Processing Letters, 2019, 49 (3): 1239- 1256. doi: 10.1007/s11063-018-9873-x
11	DONG H, SUÁREZ-PANIAGUA V, ZHANG H Y, et al. Rare disease identification from clinical notes with ontologies and weak supervision[C]//Proceedings of the 43rd Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC). Washington D.C., USA: IEEE Press, 2021: 2294-2298.
12	ANGELL R, MONATH N, MOHAN S, et al. Clustering-based inference for biomedical entity linking[C]//Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. [S. l. ]: ACL, 2021: 2598-2608.
13	张晟旗, 王元龙, 李茹, 等. 基于局部注意力机制的中文短文本实体链接. 计算机工程, 2021, 47 (11): 77-83, 92. doi: 10.19678/j.issn.1000-3428.0059493
	ZHANG S Q , WANG Y L , LI R , et al. Entity linking based on local attention mechanism for Chinese short text. Computer Engineering, 2021, 47 (11): 77-83, 92. doi: 10.19678/j.issn.1000-3428.0059493
14	饶东宁, 许正辉, 梁瑞仕. 基于知识库问答的回答生成研究. 计算机工程, 2025, 51 (2): 94- 101. doi: 10.19678/j.issn.1000-3428.0068433
	RAO D N , XU Z H , LIANG R S . Research on answer generation based on knowledge base question answering. Computer Engineering, 2025, 51 (2): 94- 101. doi: 10.19678/j.issn.1000-3428.0068433
15	UJIIE S, ISO H, YADA S, et al. End-to-end biomedical entity linking with span-based dictionary matching[EB/OL]. [2024-10-05]. https://arxiv.org/abs/2104.10493.
16	MONDAL I, PURKAYASTHA S, SARKAR S, et al. Medical entity linking using triplet network[EB/OL]. [2024-10-05]. https://arxiv.org/abs/2012.11164.
17	LIU F Y, SHAREGHI E, MENG Z Q, et al. Self-alignment pretraining for biomedical entity representations[EB/OL]. [2024-10-05]. https://arxiv.org/abs/2010.11784.
18	UJIIE S, ISO H, ARAMAKI E. Biomedical entity linking with contrastive context matching[EB/OL]. [2024-10-05]. https://arxiv.org/abs/2106.07583.
19	ZHANG S, CHENG H, VASHISHTH S, et al. Knowledge-rich self-supervision for biomedical entity linking[EB/OL]. [2024-10-05]. https://arxiv.org/abs/2112.07887.
20	DOUZE M, GUZHVA A, DENG C, et al. The FAISS library[EB/OL]. [2024-10-05]. https://arxiv.org/pdf/2401.08281.
21	LI H D , CHEN Q C , TANG B Z , et al. CNN-based ranking for biomedical entity normalization. BMC Bioinformatics, 2017, 18 (11): 385.
22	AGARWAL D, ANGELL R, MONATH N, et al. Entity linking via explicit mention-mention coreference modeling[EB/OL]. [2024-10-05]. https://openreview.net/pdf?id=f_1MD91kBza.
23	郭俊辰, 马御棠, 相艳, 等. 基于Prompt打分的实体链接方法. 计算机工程, 2025, 51 (3): 334- 341. doi: 10.19678/j.issn.1000-3428.0068442
	GUO J C , MA Y T , XIANG Y , et al. Entity linking method based on Prompt scoring. Computer Engineering, 2025, 51 (3): 334- 341. doi: 10.19678/j.issn.1000-3428.0068442
24	ZHU T, QIN Y, CHEN Q, et al. Enhancing entity representations with Prompt learning for biomedical entity linking[EB/OL]. [2024-10-05]. https://www.ijcai.org/proceedings/2022/560.
25	LE N D , NGUYEN N T H . A metric learning-based method for biomedical entity linking. Frontiers in Research Metrics and Analytics, 2023, 8, 1247094. doi: 10.3389/frma.2023.1247094
26	ORR L, LESZCZYNSKI M, ARORA S, et al. Bootleg: chasing the tail with self-supervised named entity disambiguation[EB/OL]. [2024-10-05]. https://arxiv.org/abs/2010.10363.
27	HE K M, FAN H Q, WU Y X, et al. Momentum contrast for unsupervised visual representation learning[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Washington D.C., USA: IEEE Press, 2020: 9726-9735.
28	SHRIVASTAVA A, GUPTA A, GIRSHICK R. Training region-based object detectors with online hard example mining[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Washington D.C., USA: IEEE Press, 2016: 761-769.
29	HOLTZMAN A, BUYS J, DU L, et al. The curious case of neural text degeneration[EB/OL]. [2024-10-05]. https://arxiv.org/abs/1904.09751.
30	SUI X H, ZHANG Y, SONG K H, et al. Improving zero-shot entity linking candidate generation with ultra-fine entity type information[C]//Proceedings of the 29th International Conference on Computational Linguistics. [S. l. ]: ACL, 2022: 2429-2437.
31	ONOE Y , DURRETT G . Fine-grained entity typing for domain independent entity linking. Proceedings of the AAAI Conference on Artificial Intelligence, 2020, 34 (5): 8576- 8583. doi: 10.1609/aaai.v34i05.6380
32	WOLF T, DEBUT L, SANH V, et al. HuggingFace's Transformers: state-of-the-art natural language processing[EB/OL]. [2024-10-05]. https://arxiv.org/abs/1910.03771.
33	DOǦAN R I , LEAMAN R , LU Z Y . NCBI Disease corpus: a resource for disease name recognition and concept normalization. Journal of Biomedical Informatics, 2014, 47, 1- 10.
34	MOHAN S, LI D H. MedMentions: a large biomedical corpus annotated with UMLS concepts[EB/OL]. [2024-10-05]. https://arxiv.org/abs/1902.09476.
35	KARTCHNER D, DENG J, LOHIYA S, et al. A comprehensive evaluation of biomedical entity linking models[C]//Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing. [S. l. ]: ACL, 2023: 14462-14478.
36	GARDA S , LESER U . BELHD: improving biomedical entity linking with homonym disambiguation. Bioinformatics, 2024, 40 (8): 474. doi: 10.1093/bioinformatics/btae474

[1]	YUAN Lining, FENG Wengang, LIU Zhao. Academic Paper Classification Method Based on Improved Graph Convolutional Network [J]. Computer Engineering, 2026, 52(9): 154-164.
[2]	ZHAI Sheping, MA Mengyao, ZHANG Wenjing, YANG Rui. Knowledge Graph Completion Integrating Relational Context Semantics [J]. Computer Engineering, 2026, 52(9): 113-122.
[3]	ZHENG Yuhao, LI Jianhua. Initial Phase Training Method of Class Incremental Learning Based on Class Boundary Sample Generation and Fine-Tuning [J]. Computer Engineering, 2026, 52(7): 86-93.
[4]	WU Di, ZHANG Le, CHEN Yao. Cross-Behavior Feature Regularization and Interaction Contrastive Learning Based Multi-Behavior Recommendation [J]. Computer Engineering, 2026, 52(7): 143-154.
[5]	XUE Hanbing, NI Chen, LI Yuying, GUAN Jia, FANG Kai, CUI Wenqian. Entity Canonicalization Method Based on Dual-View Contrastive Learning and Submodular Optimization [J]. Computer Engineering, 2026, 52(6): 80-95.
[6]	YU Zhengtao, SUN Ziqin, ZHANG Yongbing, GAO Shengxiang, HUANG Yuxin, TAN Kaiwen. Self-Supervised Sequence Recommendation Method Based on Random Self-Attention and Momentum Contrastive Learning [J]. Computer Engineering, 2026, 52(6): 132-140.
[7]	ZHANG Zhen, YOU Lan, PENG Qingxi, JIN Hong, ZENG Haoqiu, XIA Yuchun. XSGCL: A Lightweight Graph Contrastive Learning Framework for Recommendation [J]. Computer Engineering, 2026, 52(4): 163-175.
[8]	HE Hongguang, XIAN Yantuan, XIANG Yan. Commonsense Knowledge Graph Completion Method Based on Relation-Constrained Contrastive Learning [J]. Computer Engineering, 2026, 52(4): 122-130.
[9]	GUO Tiansheng, XIE Jinkui. Adaptive Adjustment Graph Augmentation and Representation Structures for Recommendation Model [J]. Computer Engineering, 2026, 52(2): 69-78.
[10]	LI Qiang, TAN Xingyi, ZHENG Wei, LIU Zhen, YANG Wenhai. Graph Neural Network Inference Optimization Based on Adversarial Training and Contrastive Representation Distillation [J]. Computer Engineering, 2026, 52(1): 126-135.
[11]	YU Peng, YANG Jiaqi, CHEN Xinran, HE Chaobo. Feature-enhanced Recommendation Algorithm Based on Bipartite Graph Contrastive Learning [J]. Computer Engineering, 2025, 51(7): 100-110.
[12]	YAO Xun, WANG Haipeng, HU Xinrong, YANG Jie. Multi-view Contrastive Recommendation Algorithm Based on Adaptive Enhancement [J]. Computer Engineering, 2025, 51(5): 103-113.
[13]	QIAN Lifeng, LI Jing, ZOU Xuxi, CHEN Yu, GU Yalin, WEI Xunhu. Multi-view Graph Clustering Algorithm Based on Dual Contrastive Learning and Hard Sample Mining [J]. Computer Engineering, 2025, 51(12): 82-95.
[14]	Shuang GAO, Yilun SHI, Qiaozhi XU, Lei YU. Research on Cardiac MRI Segmentation Based on Asymmetric Encoding and Decoding Structure of Contrastive Learning [J]. Computer Engineering, 2024, 50(8): 290-300.
[15]	Lai QIAN, Weiwei ZHAO. Text Classification Method Based on Contrastive Learning and Attention Mechanism [J]. Computer Engineering, 2024, 50(7): 104-111.

Please choose a citation manager

Content to export