|
|
|
| Multiagent Collaborative Entity Linking for Historical Characters in Ancient Chinese Texts |
| Yang Fan1, He Jiacheng1, Liu Chang1, Zhang Qi2, Liu Liu1 |
1.School of Information Management, Nanjing Agricultural University, Nanjing 210095
2.School of Economics and Management, Shanxi University, Taiyuan 030031 |
|
|
|
|
Abstract Historical figure entity linking in classical Chinese texts presents unique challenges that include diverse referential forms, absence of punctuation, and underdeveloped historical knowledge bases, rendering conventional entity linking methods inadequate for ancient literature processing. This study proposes a multiagent collaborative approach for historical figure entity linking in classical texts. Using the Records of the Grand Historian as the experimental corpus, a comprehensive historical figure knowledge base was constructed by integrating the China Biographical Database (CBDB) with manually annotated character-relationship data. Subsequently, we developed a collaborative framework based on the LangGraph multiagent architecture comprising three specialized agents: entity recognition, candidate entity construction, and candidate entity reranking. This method innovatively employs a dual-scoring mechanism that combines text similarity algorithms (such as BM25) with large language model (LLM) multidimensional semantic evaluation for entity mapping and ranking. Through inter-agent information exchange and negotiation mechanisms, the system achieves precise linking from textual entity mentions to standardized knowledge base entities. In experimental results, Qwen3-32B achieved optimal performance (recall@5: 0.908; accuracy: 0.947), representing improvements of 9.0% and 17.7%, respectively, over the bidirectional encoder representations from transformers (BERT) baseline. Ablation studies confirmed positive contributions from all modules, with the re-ranking mechanism showing the most significant impact, thereby validating that LLM semantic scoring is effectively enhanced by character background knowledge injection. This study presents a novel multiagent collaborative methodology for historical entity linking, offering new insights into entity linking research in the classical literature.
|
|
Received: 19 August 2025
|
|
|
|
1 Shen W, Wang J Y, Han J W. Entity linking with a knowledge base: issues, techniques, and solutions[J]. IEEE Transactions on Knowledge and Data Engineering, 2015, 27(2): 443-460.
2 张玥, 李韧, 杨建喜, 等. 基于深度神经网络的实体链接研究综述[J]. 中文信息学报, 2024, 38(8): 1-14.
3 Ganea O E, Hofmann T. Deep joint entity disambiguation with local neural attention[C]// Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing. Stroudsburg: Association for Computational Linguistics, 2017: 2619-2629.
4 刘洋, 王东波. 古籍智能信息处理研究现状[J]. 图书情报工作, 2024, 68(23): 120-138.
5 刘浏, 王东波, 黄水清, 等. 数字人文视野下的古汉语实体歧义研究[J]. 图书与情报, 2020(5): 115-124.
6 Stone P, Veloso M. Multiagent systems: a survey from a machine learning perspective[J]. Autonomous Robots, 2000, 8(3): 345-383.
7 Li G H, Hammoud H, Itani H, et al. CAMEL: communicative agents for “mind” exploration of large language model society[C]// Proceedings of the Advances in Neural Information Processing Systems 36. Red Hook: Curran Associates, 2023: 51991-52008.
8 Zhang Y, Yang S X, Bai C J, et al. Towards efficient LLM grounding for embodied multi-agent collaboration[C]// Findings of the Association for Computational Linguistics: ACL 2025. Stroudsburg: Association for Computational Linguistics, 2025: 1663-1699.
9 Rogers A, Kovaleva O, Rumshisky A. A primer in BERTology: what we know about how BERT works[J]. Transactions of the Association for Computational Linguistics, 2020, 8: 842-866.
10 贾子琦, 王健宗, 张旭龙, 等. 基于大模型的具身智能任务规划研究: 从单智能体到多智能体[J]. 大数据, 2025, 11(2): 73-90.
11 Wang J A, Meng F D, Liang Y L, et al. DRT: deep reasoning translation via long chain-of-thought[C]// Findings of the Association for Computational Linguistics: ACL 2025. Stroudsburg: Association for Computational Linguistics, 2025: 6770-6782.
12 Mnih V, Badia A P, Mirza M, et al. Asynchronous methods for deep reinforcement learning[C]// Proceedings of the 33rd International Conference on Machine Learning. New York: JMLR.org, 2016: 1928-1937.
13 Zuo K W, Jiang Y R, Mo F, et al. KG4Diagnosis: a hierarchical multi-agent LLM framework with knowledge graph enhancement for medical diagnosis[C]// Proceedings of the First AAAI Bridge Program on AI for Medicine and Healthcare. PMLR, 2025: 195-204.
14 Nadeau D, Sekine S. A survey of named entity recognition and classification[J]. Lingvistic? Investigationes, 2007, 30(1): 3-26.
15 孙艳茹, 林民, 史明伟. 融合多类型软提示与全局指针网络的古籍命名实体识别[J]. 计算机工程与应用, 2026, 62(10): 134-147.
16 张文东, 吴子炜, 宋国昌, 等. 基于SiKuBERT与多元数据嵌入的中医古籍命名实体识别[J]. 华南理工大学学报(自然科学版), 2024, 52(6): 128-137.
17 朱锁玲, 包平. 方志类古籍地名识别及分析研究——以《方志物产》(广东分卷)为例[J]. 图书馆论坛, 2012, 32(4): 171-176.
18 王世昆. 中医症状病机实体识别及其关系挖掘研究[D]. 厦门: 厦门大学, 2009.
19 李娜. 基于条件随机场的方志古籍别名自动抽取模型构建[J]. 中文信息学报, 2018, 32(11): 41-48, 61.
20 孟洪宇, 谢晴宇, 常虹, 等. 基于条件随机场的《伤寒论》中医术语自动识别[J]. 北京中医药大学学报, 2015, 38(9): 587-590.
21 刘浏, 秦天允, 王东波. 非物质文化遗产传统音乐术语自动抽取[J]. 数据分析与知识发现, 2020, 4(12): 68-75.
22 杜悦, 王东波, 江川, 等. 数字人文下的典籍深度学习实体自动识别模型构建及应用研究[J]. 图书情报工作, 2021, 65(3): 100-108.
23 林立涛, 王东波, 刘江峰, 等. 数字人文视域下典籍动物命名实体识别研究——以SikuBERT预训练模型为例[J]. 图书馆论坛, 2022, 42(10): 42-50.
24 谢靖, 刘江峰, 王东波. 古代中国医学文献的命名实体识别研究——以Flat-lattice增强的SikuBERT预训练模型为例[J]. 图书馆论坛, 2022, 42(10): 51-60.
25 斯日古楞, 林民, 郭振东, 等. 基于提示学习和抽取式阅读理解的古籍礼仪实体关系联合抽取方法研究[J]. 数据分析与知识发现, 2025, 9(3): 147-159.
26 张逸勤, 邓三鸿, 王东波. 基于生成式大语言模型的非遗文本嵌套命名实体识别研究[J]. 现代情报, 2025, 45(10): 26-38.
27 刘畅, 张琪, 王东波, 等. 基于大语言模型技术的古籍限定域关系抽取及应用研究[J]. 情报学报, 2025, 44(2): 200-219.
28 Moreno J G, Besan?on R, Beaumont R, et al. Combining word and entity embeddings for entity linking[C]// Proceedings of the 14th International Conference on the Semantic Web. Cham: Springer, 2017: 337-352.
29 Taneva B, Cheng T, Chakrabarti K, et al. Mining acronym expansions and their meanings using query click log[C]// Proceedings of the 22nd International Conference on World Wide Web. New York: ACM Press, 2013: 1261-1272.
30 Li D, Fu Z J, Zheng Z Y. An entity linking model based on candidate features[J]. Social Network Analysis and Mining, 2021, 11(1): 50.
31 Wang J T, Qu J Y, Zhao Z Y, et al. SMAAMA: a named entity alignment method based on Siamese network character feature and multi-attribute importance feature for Chinese civil aviation[J]. Journal of King Saud University Computer and Information Sciences, 2023, 35(10): 101856.
32 Sun Y M, Lin L, Tang D Y, et al. Modeling mention, context and entity with neural networks for entity disambiguation[C]// Proceedings of the 24th International Conference on Artificial Intelligence. Palo Alto: AAAI Press, 2015: 1333-1339.
33 Le P, Titov I. Distant learning for entity linking with automatic noise detection[C]// Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics. Stroudsburg: Association for Computational Linguistics, 2019: 4081-4090.
34 Ratinov L, Roth D, Downey D, et al. Local and global algorithms for disambiguation to wikipedia[C]// Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies. Stroudsburg: Association for Computational Linguistics, 2011: 1375-1384.
35 Zhang W, Su J, Tan C L, et al. Entity linking leveraging automatically generated annotation[C]// Proceedings of the 23rd International Conference on Computational Linguistics. Stroudsburg: Association for Computational Linguistics, 2010: 1290-1298.
36 Fang Z, Cao Y N, Li Q, et al. Joint entity linking with deep reinforcement learning[C]// Proceedings of the World Wide Web Conference. New York: ACM Press, 2019: 438-447.
37 Francis-Landau M, Durrett G, Klein D. Capturing semantic similarity for entity linking with convolutional neural networks[C]// Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. Stroudsburg: Association for Computational Linguistics, 2016: 1256-1261.
38 Huang H Z, Heck L P, Ji H. Leveraging deep neural networks and knowledge graphs for entity disambiguation[PP/OL]. V1. arXiv (2015-04-28). https://arxiv.org/pdf/1504.07678.
39 Shahbazi H, Fern X Z, Ghaeini R, et al. Entity-aware ELMo: learning contextual entity representation for entity disambiguation[PP/OL]. V2. arXiv (2019-08-22). https://doi.org/10.48550/arXiv.1908.05762.
40 Yamada I, Washio K, Shindo H, et al. Global entity disambiguation with pretrained contextualized embeddings of words and entities[PP/OL]. V3. arXiv (2021-11-24). https://arxiv.org/pdf/1909.00426v3.
41 Chen Z B, Wu Y T, Feng Y S, et al. Integrating manifold knowledge for global entity linking with heterogeneous graphs[J]. Data Intelligence, 2022, 4(1): 20-40.
42 Ji Z C, Wei Q, Xu H. BERT-based ranking for biomedical entity normalization[J]. AMIA Joint Summits on Translational Science Proceedings, 2020, 2020: 269-277.
43 Kolitsas N, Ganea O E, Hofmann T. End-to-end neural entity linking[C]// Proceedings of the 22nd Conference on Computational Natural Language Learning. Stroudsburg: Association for Computational Linguistics, 2018: 519-529.
44 Martins P H, Marinho Z, Martins A F T. Joint learning of named entity recognition and entity linking[C]// Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics: Student Research Workshop. Stroudsburg: Association for Computational Linguistics, 2019: 190-196.
45 中国历代人物传记资料库(CBDB)[DB/OL]. [2026-05-27]. https://projects.iq.harvard.edu/chinesecbdb/home.
46 张琪, 王东波, 黄水清, 等. 史书多维知识重组与可视化研究——以《史记》为对象[J]. 情报学报, 2022, 41(2): 130-141.
47 刘江峰, 冯钰童, 王东波, 等. 数字人文视域下SikuBERT增强的史籍实体识别研究[J]. 图书馆论坛, 2022, 42(10): 61-72.
48 Douze M, Guzhva A, Deng C Q, et al. The FAISS library[J]. IEEE Transactions on Big Data, 2026, 12(2): 346-361.
49 Manning C D, Raghavan P, Schütze H. Introduction to information retrieval[M]. Cambridge: Cambridge University Press, 2008.
50 Robertson S, Zaragoza H. The probabilistic relevance framework: BM25 and beyond[J]. Foundations and Trends in Information Retrieval, 2009, 3(4): 333-389.
51 Navarro G. A guided tour to approximate string matching[J]. ACM Computing Surveys, 2001, 33(1): 31-88.
52 Real R, Vargas J M. The probabilistic basis of Jaccard’s index of similarity[J]. Systematic Biology, 1996, 45(3): 380-385.
53 Cohen W W, Ravikumar P, Fienberg S E. A comparison of string distance metrics for name-matching tasks[C]// Proceedings of the 2003 International Conference on Information Integration on the Web. Palo Alto: AAAI Press, 2003: 73-78.
54 Zhang Y Z, Li M X, Long D K, et al. Qwen3 Embedding: advancing text embedding and reranking through foundation models[PP/OL]. V3. arXiv (2025-06-11). https://arxiv.org/pdf/2506.05176.
55 张越, 王长征, 苏雪峰, 等. 基于标签语义信息感知的少样本命名实体识别方法[J]. 北京大学学报(自然科学版), 2024, 60(3): 413-421. |
|
|
|
