计算机科学

计算机科学 ›› 2026, Vol. 53 ›› Issue (7): 156-167.doi: 10.11896/jsjkx.250500006

• 人工智能 • 上一篇    下一篇

基于层次依赖聚合和事件增强的文档级事件论元抽取模型

丁志君1, 艾芳菊1,2,3, 刘艾环4   

  1. 1 湖北大学计算机学院 武汉 430062
    2 大数据智能分析与行业应用湖北省重点实验室(湖北大学) 武汉 430062
    3 智慧政务与人工智能应用湖北省工程研究中心 武汉 430062
    4 马来西亚理科大学计算机科学学院 马来西亚 槟城 11800
  • 收稿日期:2025-05-06 修回日期:2025-08-12 出版日期:2026-07-15 发布日期:2026-07-10
  • 通讯作者: 艾芳菊(576925402@qq.com)
  • 作者简介:(18736148521@163.com)
  • 基金资助:
    湖北省自然科学基金青年项目(2023AFB313)

Document-level Event Argument Extraction Model Based on Hierarchical Dependency Aggregation and Event Enhancement

DING Zhijun1, AI Fangju1,2,3, LIU Aihuan4   

  1. 1 School of Computer Science,Hubei University,Wuhan 430062,China
    2 Hubei Key Laboratory of Big Data Intelligent Analysis and Application(Hubei University),Wuhan 430062,China
    3 Engineering Research Center of Hubei Province in Intelligent Government Affairs and Application of Artificial Intelligence,Wuhan 430062,China
    4 School of Computer Science,University of Science Malaysia,Penang 11800,Malaysia
  • Received:2025-05-06 Revised:2025-08-12 Published:2026-07-15 Online:2026-07-10
  • About author:DING Zhijun,born in 1999,postgra-duate,is a member of CCF(No.A00667G).His main research interests include natural language processing and event argument extraction.
    AI Fangju,born in 1973,Ph.D,associate professor.Her main research interests include natural language processing and data mining.
  • Supported by:
    Young Program of the Natural Science Foundation of Hubei Province,China(2023AFB313).

PDF (PC)

22

摘要： 在文档级事件论元抽取任务中,现有基于提示学习的模型难以全面理解文档的整体语义,并且忽略了文档与提示模板之间的交互。对此,提出一种基于层次依赖聚合和事件增强机制的文档级事件论元抽取模型。首先,通过BART获取输入序列的向量表示。然后,提出由语义层次依赖感知机制和结构层次依赖感知机制组成的层次依赖聚合结构,分别捕捉实体提及间的语义关联和结构信息,并通过自注意力机制动态融合。接着,利用融合关系矩阵引导关系依存图中更多的上下文信息聚合到相应实体提及上,从而更新提及表示;该提及表示被加入到原始输入表示,以增强模型对实体关系的感知能力及文档与提示模板之间的交互能力。最后,通过事件增强机制使模型聚焦于与当前抽取事件相关的上下文信息,减少信息干扰和冗余,提高论元抽取的准确性。在两个公开数据集RAMS和WikiEvent上进行了模型验证,实验结果表明,所提模型的F1值均优于对比模型,综合性能得到有效提升。

关键词: 文档级事件论元抽取, 提示学习, 层次依赖聚合, 自注意力机制, 事件增强机制

Abstract: In the task of document-level event argument extraction,existing prompt-based learning models face challenges in comprehensively capturing the holistic semantic understanding of documents and neglect the interaction between documents and prompt templates.To address these limitations,a novel document-level event argument extraction model is proposed,incorporating hierarchical dependency aggregation and an event enhancement mechanism.Initially,the vector representations of the input sequence are obtained through BART.Subsequently,a hierarchical dependency aggregation architecture is introduced,consisting of a semantic hierarchical dependency-aware mechanism and a structural hierarchical dependency-aware mechanism,designed to capture semantic correlations and structural information among entity mentions respectively.These features are dynamically fused via a self-attention mechanism.The integrated relation matrix is then leveraged to guide the aggregation of contextual information from relational dependency graphs onto corresponding entity mentions,thereby updating mention representations.These enhanced representations are subsequently incorporated into the original input representations to strengthen the model's capability in perceiving entity relations and facilitating document-prompt template interactions.Finally,an event enhancement mechanism is implemented to prioritize contextually relevant information for the current extraction task while mitigating information redundancy and interference,ultimately improving argument extraction accuracy.Experimental results conducted on RAMS and WikiEvent two public dataset demonstrate that the proposed model achieves superior F1 scores compared to baseline models,with significant improvements in comprehensive performance metrics.

Key words: Document-level event argument extraction, Prompt learning, Hierarchical dependency aggregation, Self-attention mechanism, Event enhancement mechanism

中图分类号: 

  • TP391
[1]DODDINGTON G R,MITCHELL A,PRZYBOCKI M A,et al.The automatic content extraction(ACE) program-tasks,data,and evaluation[C]//Proceedings of the 4th International Conference on Language Resources And Evaluation.2004:837-840.
[2]VASWANI A,SHAZEER N,PARMAR N,et al.Attention isall you need[C]//Proceedings of the 31st International Confe-rence on Neural Information Processing Systems.2017:6000-6010.
[3]EBNER S,XIA P,CULKIN R,et al.Multi-sentence argument linking[C]//Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics.2020:8057-8077.
[4]LI S,JI H,HAN J.Document-level event argument extraction by conditional generation[C]//Proceedings of Conference of the North American Chapter of the Association for Computational Linguistics:Human Language Technologies.2021:894-908.
[5]LUO N,DU X,HE Y,et al.A framework for document-levelcybersecurity event extraction from open source data[C]//Proceedings of the IEEE 24th International Conference on Compu-ter Supported Cooperative Work in Design.2021:422-427.
[6]WANG L,LI R X,LI Y H,et al.Joint Model for Document-Level Event Extraction Without Triggers[J].Frontiers of Computer Science and Technology,2021,15(12):2327-2334.
[7]ZHONG W F,YANG H,CHEN Y B,et al.Document-level Event Extraction Based on Joint Labeling and Global Reasoning[J].Chinese Information Processing,2019,33(9):88-95.
[8]DEVLIN J,CHANG M,LEE K,et al.BERT:pretraining ofdeep bidirectional transformers for language understanding[C]//Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics:Human Language Technologies.2019:4171-4186.
[9]LEWIS M,LIU Y,GOYAL N,et al.BART:denoising sequence-to-sequence pre-training for natural language generation,translation,and comprehension[C]//Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics.2020:7871-7880.
[10]SHI P,LIN J.Simple bert models for relation extraction and semantic role labeling[EB/OL].(2019-04-10)[2025-03-06].https://arxiv.org/abs/1904.05255.
[11]LIN Y,JI H,HUANG F,et al.A Joint Neural Model for Information Extraction with Global Features[C]//Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics.2020:7999-8009.
[12]DU X Y,CARDIE C.Event extraction by answering(Almost) natural questions [C]//Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing.2020:671-683
[13]LIU J,CHEN Y,XU J.Machine reading comprehension as data augmentation:A case study on implicit event argument extraction[C]//Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing.2021:2716-2725.
[14]LI F,PENG W,CHEN Y,et al.Event extraction as multi-turn question answering[C]//Findings of the Association for Computational Linguistics:EMNLP 2020.2020:829-838.
[15]ZHOU X L,LIANG Y L,GUO R F,et al.Event Argument Extraction Using Pre-trained Multi-pooling Attention Models[J].Journal of Chinese Computer Systems,2025,46(5):1064-1071.
[16]ZENG Q,ZHAN Q,HENG J.EA2E:Improving Consistencywith Event Awareness for Document-Level Argument Extraction[C]//Findings of the Association for Computational Linguistics:NAACL 2022.2022:2649-2655.
[17]XU R,WANG P,LIU T,et al.A two-stream AMR-enhanced model for document-level event argument extraction[C]//Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics:Human Language Technologies.2022:5025-5036.
[18]LIU W L,CHENG S H,ZENG D Y,et al.Enhancing Docu-ment-level Event Argument Extraction with Contextual Clues and Role Relevance[C]//Findings of the Association for Computational Linguistics:ACL 2023.2023:12908-12922.
[19]BANARESCU L,BONIAL C,CAI S,et al.Abstract Meaning Representation for Sembanking[C]//Proceedings of the 7th Linguistic Annotation Workshop & Interoperability with Discourse.2013:178-186.
[20]MA Y,WANG Z,CAO Y,et al.Prompt for extraction?paie:prompting argument interaction for event argument extraction[C]//Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics.2022:6759-6774.
[21]ZHANG J,YANG C,ZHU H,et al.A Semantic Mention Graph Augmented Model for Document-Level Event Argument Extraction[C]//Proceedings of the 2024 Joint International Conference on Computational Linguistics,Language Resources and Evaluation(LREC-COLING 2024).2024:1577-1587.
[22]ZHOU H Z,QIAN J L,FENG Z J,et al.LLMs Learn Task Heuristics from Demonstrations:A Heuristic-Driven Prompting Strategy for Document-Level Event Argument Extraction[C]//Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics.2024:11972-11990.
[23]SUN T Y,XIAO J Y.Enhancing Document-level Argument Extraction with Definition-augmented Heuristic-driven Prompting for LLMs[C]//Proceedings of the 38th Pacific Asia Conference on Language,Information and Computation.2024:380-388.
[24]KIPF T N,WELLING M.Semi-supervised classification withgraph convolutional networks [EB/OL].(2017-02-22) [2025-03-06].https://doi.org/10.48550/arXiv.1609.02907.
Viewed
Full text


Abstract

Cited
  Shared   
  Discussed   
No Suggested Reading articles found!
渝ICP备16013121号-4
地址：重庆市两江新区洪湖西路18号    邮编：401121  
电话：023-63500828（编辑部） 023-67039612（会议/专题） 023-67039623（财务/发票）
E-mail：jsjkx12@163.com
本系统由北京玛格泰克科技发展有限公司设计开发