基于Longformer和对比学习的实体链接方法
Entity Linking Method Based on Longformer and Comparative Learning
DOI: 10.12677/csa.2025.155129, PDF,    科研立项经费支持
作者: 赵占芳, 刘佳琪：河北地质大学信息工程学院，河北 石家庄
关键词: 实体链接；知识图谱；预训练模型；对比学习；Entity Linking； Knowledge Graph； Pre-Trained Mode； Contrastive Learning
摘要: 实体链接是自然语言处理中的核心任务，旨在将文本中的实体与知识库中的标准实体进行精确匹配。为了应对传统的实体链接方法在长文本处理时难以捕捉长距离依赖关系，本文提出了一种基于Longformer和对比学习的端到端实体链接方法，用更加精细化的模块设计来专门优化长文本中的实体链接性能。通过融合Longformer在长序列文本处理中的优势与对比学习在优化实体匹配过程中的机制，设计了一个联合优化实体识别和链接任务的框架，从而有效提升了模型在复杂文本中的表现。在实验验证中，本文采用了AIDA-CoNLL英文标准数据集，结果表明所提出的方法在F1值上相较于现有主流方法有了1.8%至11.8%的显著提升。
Abstract: Entity linking is a core task in natural language processing, aiming to precisely match entities mentioned in text with their corresponding standardized entities in a knowledge base. To address the challenges faced by traditional entity linking methods in capturing long-range dependencies within lengthy texts, this paper proposes an end-to-end entity linking approach based on Longformer and contrastive learning. The method incorporates a more refined module design specifically tailored to optimize entity linking performance in long texts. By leveraging the strengths of Longformer in processing long-sequence texts and the mechanisms of contrastive learning for enhancing entity matching, we design a unified framework that jointly optimizes entity recognition and linking tasks, thereby significantly improving the model’s performance on complex texts. In the experimental evaluation, we utilize the AIDA-CoNLL benchmark dataset, and the results demonstrate that the proposed method achieves a notable improvement in F1 score, ranging from 1.8% to 11.8%, compared to existing state-of-the-art methods.
文章引用：赵占芳, 刘佳琪. 基于Longformer和对比学习的实体链接方法[J]. 计算机科学与应用, 2025, 15(5): 564-572. https://doi.org/10.12677/csa.2025.155129

参考文献

[1] Chen, S., Wang, J., Jiang, F. and Lin, C. (2020) Improving Entity Linking by Modeling Latent Entity Type Information. Proceedings of the AAAI Conference on Artificial Intelligence, 34, 7529-7537. [Google Scholar] [CrossRef] 
[2] Sevgili, Ö., Shelmanov, A., Arkhipov, M., Panchenko, A. and Biemann, C. (2022) Neural Entity Linking: A Survey of Models Based on Deep Learning. Semantic Web, 13, 527-570. [Google Scholar] [CrossRef] 
[3] Shen, W., Wang, J. and Han, J. (2015) Entity Linking with a Knowledge Base: Issues, Techniques, and Solutions. IEEE Transactions on Knowledge and Data Engineering, 27, 443-460. [Google Scholar] [CrossRef] 
[4] Cao, Y.X., Hou, L., Li, J.Z. and Liu, Z.Y. (2018) Neural Collective Entity Linking. Proceedings of the 27th International Conference on Computational Linguistics, Santa Fe, 20-26 August 2018, 675-686.
[5] Beltagy, I., Peters, M.E. and Cohan, A. (2020) Longformer: The Long-Document Transformer.
[6] Broscheit, S. (2019) Investigating Entity Knowledge in BERT with Simple Neural End-to-End Entity Linking. Proceedings of the 23rd Conference on Computational Natural Language Learning (CoNLL), Hong Kong, November 2019, 677-685. [Google Scholar] [CrossRef] 
[7] Young, T., Hazarika, D., Poria, S. and Cambria, E. (2018) Recent Trends in Deep Learning Based Natural Language Processing [Review Article]. IEEE Computational Intelligence Magazine, 13, 55-75. [Google Scholar] [CrossRef] 
[8] De Cao, N., Aziz, W. and Titov, I. (2021) Highly Parallel Autoregressive Entity Linking with Discriminative Correction. Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, November 2021, 7662-7669. [Google Scholar] [CrossRef] 
[9] Kolitsas, N., Ganea, O. and Hofmann, T. (2018) End-to-End Neural Entity Linking. Proceedings of the 22nd Conference on Computational Natural Language Learning, Brussels, 31 October-1 November 2018, 519-529. [Google Scholar] [CrossRef] 
[10] 李天然, 刘明童, 张玉洁, 等. 基于深度学习的实体链接研究综述[J]. 北京大学学报(自然科学版), 2021, 57(1): 91-98.
[11] Jia, B., Wang, C., Zhao, H. and Shi, L. (2022) An Entity Linking Algorithm Derived from Graph Convolutional Network and Contextualized Semantic Relevance. Symmetry, 14, Article No. 2060. [Google Scholar] [CrossRef] 
[12] Zhang, W., Hua, W. and Stratos, K. (2021) EntQA: Entity Linking as Question Answering.
[13] Poerner, N., Waltinger, U. and Schütze, H. (2020) E-BERT: Efficient-yet-Effective Entity Embeddings for BERT. Findings of the Association for Computational Linguistics: EMNLP 2020, November 2020, 803-818. [Google Scholar] [CrossRef] 
[14] De Cao, N., Izacard, G., Riedel, S., et al. (2020) Autoregressive Entity Retrieval.
[15] Peters, M.E., Neumann, M., Logan, R., Schwartz, R., Joshi, V., Singh, S., et al. (2019) Knowledge Enhanced Contextual Word Representations. Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), Hong Kong, November 2019, 43-54. [Google Scholar] [CrossRef] 
[16] Humeau, S., et al. (2019) Poly-Encoders: Architectures and Pre-Training Strategies for Fast and Accurate Multi-Sentence Scoring. International Conference on Learning Representations, New Orleans, 6-9 May 2019, pages.
[17] Tsai, C.T., Upadhyay, S. and Roth, D. (2025) Introduction to Entity Discovery and Linking. Multilingual Entity Linking, Springer Nature Switzerland, 1-14. [Google Scholar] [CrossRef] 
[18] Zhong, L., Wu, J., Li, Q., et al. (2023) A Comprehensive Survey on Automatic Knowledge Graph Construction. ACM Computing Surveys, 56, 1-62. [Google Scholar] [CrossRef] 
[19] Hoffart, J., Yosef, M.A., Bordino, I., et al. (2011) Robust Disambiguation of Named Entities in Text. Proceedings of the 2011 Conference on Empirical Methods in Natural Language Processing, Edinburgh, 27-29 July 2011, 782-792.
[20] Miyato, T., Dai, A.M. and Goodfellow, I. (2016) Adversarial Training Methods for Semi-Supervised Text Classification.