计算机科学

计算机科学 ›› 2025, Vol. 52 ›› Issue (9): 303-312.doi: 10.11896/jsjkx.240800121

• 人工智能 • 上一篇    下一篇

基于提示学习与超图的事件因果关系识别模型

程章桃1, 黄浩燃1, 薛荷2,3, 刘乐源1, 钟婷1, 周帆1   

  1. 1 电子科技大学信息与软件工程学院 成都 610054
    2 应急管理部四川消防研究所 成都 610036
    3 四川大学计算机学院 成都 610065
  • 收稿日期:2024-08-23 修回日期:2024-12-03 出版日期:2025-09-15 发布日期:2025-09-11
  • 通讯作者: 刘乐源(leyuanliu@uestc.edu.cn)
  • 作者简介:(zhangtao.cheng@outlook.com)
  • 基金资助:
    国家自然科学基金(U2336204,62176043,62072077)

Event Causality Identification Model Based on Prompt Learning and Hypergraph

CHENG Zhangtao1, HUANG Haoran1, XUE He2,3, LIU Leyuan1, ZHONG Ting1, ZHOU Fan1   

  1. 1 School of Information and Software Engineering,University of Electronic Science and Technology of China,Chengdu 610054,China
    2 Sichuan Fire Research Institute of MEM,Chengdu 610036,China
    3 College of Computer Science,Sichuan University,Chengdu 610065,China
  • Received:2024-08-23 Revised:2024-12-03 Online:2025-09-15 Published:2025-09-11
  • About author:CHENG Zhangtao,born in 1998,postgraduate.His main research interests include machine learning,data mining and recommender systems.
    LIU Leyuan,born in 1982,Ph.D,research associate.His main research interests include graph learning,social network data mining and event prediction.
  • Supported by:
    National Natural Science Foundation of China(U2336204,62176043,62072077).

PDF (PC)

11

摘要： 事件因果关系识别是自然语言处理领域的重要研究方向,其任务目标是识别两个特定事件间是否存在因果关联。当前的主流方法通常采用预训练语言模型从文本中提取有限的上下文语义信息,从而判别事件间的因果关系。然而,此类方法仅简单理解关键事件结构及其上下文语义信息,并未充分利用预训练语言模型的能力,同时忽略了历史事件与相关标签在构建类比推理以确定目标事件间因果关系上的重要作用。为了应对上述挑战,提出一种基于提示学习与超图增强的模型(Prompt Learning and Hypergraph Enhanced Model,PLHGE)。该模型能够充分捕捉事件之间的全局交互信息及当前事件与历史事件之间的事件结构与语义联系,通过融合描述性知识与文本语义,生成层次化的事件结构;通过构建基于知识的超图,融入细粒度及文档级语义信息,提升了识别能力;此外,引入基于关系性知识的提示学习模块,利用预训练语言模型中的潜在因果知识来提升对事件因果关系的识别能力。最后,在两个公开基准数据集上进行了广泛的实验,实验结果表明,PLHGE模型在因果关系识别任务中优于现有的基线模型。

关键词: 事件因果关系识别, 自然语言处理, 提示学习, 超图

Abstract: Event causality identification(ECI) is a crucial research direction in the field of natural language processing,with the objective of accurately identifying whether the causal relations exists between two specific events.Current mainstream methods often utilize pre-trained language models to extract limited contextual semantic information from text to judge causal relationships.However,such methods tend to simplify the understanding of key event structures and their contextual semantics,failing to fully leverage the capabilities of pre-trained language models.Additionally,they overlook the significant role of historical events and relevant labels in constructing analogical reasoning to establish causal relations between target events.To address these challenges,model based on a prompt learning and hypergraph enhanced model(PLHGE) is proposed.The proposed model effectively captures global interaction patterns among events and the structural-semantic connections between current and historical events.By integrating descriptive knowledge with textual semantics,the model generates a hierarchical event structure.Additionally,PLHGE constructs a knowledge-based hypergraph to incorporate fine-grained and document-level semantic information,thereby enhancing its identification ability.Furthermore,a relationship-based knowledge prompt learning module is introduced to utilize latent causal knowledge within pre-trained language models to improve event causal relationship recognition.Finally,extensive experiments conduct on two public benchmark datasets,and the results demonstrate that PLHGE model outperforms existing baselines in the ECI task.

Key words: Event causality identification, Natural language processing, Prompt learning, Hypergraph

中图分类号: 

  • TP391
[1]DING X,LI Z,LIU T,et al.ELG:an event logic graph[J].ar-Xiv:1907.08015,2019.
[2]WEN K Y,JI W T,SONG B Y.Bi-graph-based Document-level Relation Extraction with Local Context Fusion[J].Journal of Chinese Computer Systems,2025,46(3):535-541
[3]SHI J,CAO S,HOU L,et al.TransferNet:An Effective andTransparent Framework for Multi-hop Question Answering over Relation Graph[C]//Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing.2021:4149-4158.
[4]ZHAO L.Event prediction in the big data era:A systematic survey[J].ACM Computing Surveys,2021,54(5):1-37.
[5]JANNACH D,MANZOOR A,CAI W,et al.A survey on conversational recommender systems[J].ACM Computing Surveys,2021,54(5):1-36.
[6]LIU J,CHEN Y,ZHAO J.Knowledge enhanced event causality identification with mention masking generalizations[C]//Proceedings of the Twenty-ninth International Conference on international Joint Conferences on Artificial Intelligence.2021:3608-3614.
[7]ZUO X,CAO P,CHEN Y,et al.LearnDA:Learnable Know-ledge-Guided Data Augmentation for Event Causality Identification[C]//Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing.2021:3558-3571.
[8]CAO P,ZUO X,CHEN Y,et al.Knowledge-enriched event causality identification via latent structure induction networks[C]//Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing.2021:4862-4872.
[9]DEVLIN J.Bert:Pre-training of deep bidirectional transformers for language understanding[J].arXiv:1810.04805,2018.
[10]SPEER R,CHIN J,HAVASI C.Conceptnet 5.5:An open multilingual graph of general knowledge[C]//Proceedings of the AAAI Conference on Artificial Intelligence.2017:4444-4451.
[11]PENNINGTON J,SOCHER R,MANNING C D.Glove:Global vectors for word representation[C]//Proceedings of the 2014 Conference on Empirical Methods in Natural Language Proces-sing(EMNLP).2014:1532-1543.
[12]GAO L,CHOUBEY P K,HUANG R.Modeling document-level causal structures for event causal relation identification[C]//Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics:Human Language Technologies.2019:1808-1817.
[13]PHU M T,NGUYEN T H.Graph convolutional networks for event causality identification with rich document-level structures[C]//Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics:Human Language Technologies.2021:3480-3490.
[14]CHEN M,CAO Y,DENG K,et al.ERGO:Event Relational Graph Transformer for Document-level Event Causality Identification[C]//Proceedings of the 29th International Conference on Computational Linguistics.2022:2118-2128.
[15]KIPF T N,WELLING M.Semi-supervised classification withgraph convolutional networks[J].arXiv:1609.02907,2016.
[16]HOFSTADTER D R.Fluid concepts and creative analogies:Computer models of the fundamental mechanisms of thought[M].Basic Books,1995.
[17]RIAZ M,GIRJU R.Toward a better understanding of causality between verbal events:Extraction and analysis of the causal power of verb-verb associations[C]//Proceedings of the SIGDIAL 2013 Conference.2013:21-30.
[18]HU Z,RAHIMTOROGHI E,WALKER M.Inference of Fine-Grained Event Causality from Blogs and Films[C]//Proceedings of the Events and Stories in the News Workshop.2017:52-58.
[19]BEAMER B,GIRJU R.Using a bigram event model to predict causal potential[C]//International Conference on intelligent Text Processing and Computational Linguistics.Berlin:Springer,2009:430-441.
[20]HASHIMOTO C,TORISAWA K,KLOETZER J,et al.Toward future scenario generation:Extracting event causality exploiting semantic relation,context,and association features[C]//Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics.2014:987-997.
[21]RIAZ M,GIRJU R.Recognizing causality in verb-noun pairs via noun and verb semantics[C]//Proceedings of the EACL 2014 Workshop on Computational Approaches to Causality in Language(CAtoCL).2014:48-57.
[22]DO Q,CHAN Y S,ROTH D.Minimally supervised event causality identification[C]//Proceedings of the 2011 Conference on Empirical Methods in Natural Language Processing.2011:294-303.
[23]KRUENGKRAI C,TORISAWA K,HASHIMOTO C,et al.Improving event causality recognition with multiple background knowledge sources using multi-column convolutional neural networks[C]//Proceedings of the AAAI Conference on Artificial Intelligence.2017:3466-3473.
[24]KADOWAKI K,IIDA R,TORISAWA K,et al.Event causality recognition exploiting multiple annotators’ judgments and background knowledge[C]//Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing.2019:5816-5822.
[25]ZUO X,CHEN Y,LIU K,et al.KnowDis:Knowledge Enhanced Data Augmentation for Event Causality Detection via Distant Supervision[C]//Proceedings of the 28th International Confe-rence on Computational Linguistics.2020:1544-1550.
[26]DEVLIN J,CHANG M W,LEE K,et al.Bert:Pre-training of deep bidirectional transformers for language understanding[J].arXiv:1810.04805,2018.
[27]SHEN S,ZHOU H,WU T,et al.Event causality identification via derivative prompt joint learning[C]//Proceedings of the 29th International Conference on Computational Linguistics.2022:2288-2299.
[28]BRETTO A.Hypergraph theory[M].Cham:Springer,2013.
[29]XIA X,YIN H,YU J,et al.Self-supervised hypergraph convolutional networks for session-based recommendation[C]//Proceedings of the AAAI Conference on Artificial Intelligence.2021:4503-4511.
[30]ZHANG H,LIU X,ZHANG J.HEGEL:Hypergraph Trans-former for Long Document Summarization[C]//Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing.2022:10167-10176.
[31]FENG Y,YOU H,ZHANG Z,et al.Hypergraph neural networks[C]//Proceedings of the AAAI Conference on Artificial Intelligence.2019:3558-3565.
[32]YADATI N,NIMISHAKAVI M,YADAV P,et al.Hypergcn:A new method for training graph convolutional networks on hypergraphs[J].Advances in Neural Information Processing Systems,2019,32:1511-1522.
[33]ANTELMI A,CORDASCO G,POLATO M,et al.A survey on hypergraph representation learning[J].ACM Computing Surveys,2023,56(1):1-38.
[34]XIA L,HUANG C,ZHANG C.Self-supervised hypergraphtransformer for recommender systems[C]//Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining.2022:2100-2109.
[35]GU Y,HAN X,LIU Z,et al.PPT:Pre-trained Prompt Tuning for Few-shot Learning[C]//Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics.2022:8410-8423.
[36]FENSEL D,ŞIMŞEK U,ANGELE K,et al.Introduction:what is a knowledge graph?[M]//Knowledge Praphs.Cham:Springer,2020:1-10.
[37]BOSSELUT A,RASHKIN H,SAP M,et al.COMET:Com-monsense Transformers for Automatic Knowledge Graph Construction[C]//Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics.2019:4762-4779.
[38]HAGBERG A,CONWAY D.Networkx:Network analysis with python[EB/OL].https://networkx.github.io,2020.
[39]ZHUANG L,WAYNE L,YA S,et al.A Robustly Optimized BERT Pre-training Approach with Post-training[C]//Procee-dings of the 20th Chinese National Conference on Computational Linguistics.2021:1218-1227.
[40]BELTAGY I,PETERS M E,COHAN A.Longformer:Thelong-document transformer[J].arXiv:2004.05150,2020.
[41]VASWANI A,SHAZEER N,PARMAR N,et al.Attention isall you need[C]//Advances in Neural Information Processing Systems.2017.
[42]ASELLI T,VOSSEN P.The event storyline corpus:A newbenchmark for causal and temporal relation extraction[C]//Proceedings of the Events and Stories in the News Workshop.2017:77-86.
[43]KOLOMIYETS O,MORNS M F,PAIMER M,et al.Annotating causality in the TempEval-3 corpus[C]//Proceedings of the EACL 2014 Workshop on Computational Approaches to Causa-lity in Language(CAtoCL).2014:10-19.
[44]LOSHCHILOV I,HUTTER F.Decoupled weight decay regularization[J].arXiv:1711.05101,2017.
[45]CHEN M,CAO Y,ZHANG Y,et al.CHEER:Centrality-aware high-order event reasoning network for document-level event causality identification[C]//Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics.ACL,2023:10804-10816.
[46]LIU J,ZHANG Z,GUO Z,et al.Kept:Knowledge enhancedprompt tuning for event causality identification[J].Knowledge-Based Systems,2023,259:110064.
[47]DING L,CHEN J,DU P,et al.Event causality identification via graph contrast-based knowledge augmented networks[J].Information Sciences,2024,656:119905.
[48]YUAN C,HUANG H Y,CAO Y,et al.Discriminative Reasoning with Sparse Event Representation for Document-level Event-Event Relation Extraction[C]//Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics.2023:16222-16234.
[49]KIM S,LEE S Y,GAO Y,et al.A survey on hypergraph neural networks:an in-depth and step-by-step guide[C]//Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining.2024:6534-6544.
[50]XING J,LIU J,WANG J,et al.A survey of efficient fine-tuning methods for Vision-Language Models－Prompt and Adapter[J].Computers & Graphics,2024,119:103885.
[51]LIANG K,MENG L,LIU M,et al.A survey of knowledgegraph reasoning on graph types:Static,dynamic,and multi-modal[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2024,12:9456-9478.
[52]CAO J,FANG J,MENG Z,et al.Knowledge graph embedding:A survey from the perspective of representation spaces[J].ACM Computing Surveys,2024,56(6):1-42.
Viewed
Full text


Abstract

Cited
  Shared   
  Discussed   
No Suggested Reading articles found!
渝ICP备16013121号-4
地址：重庆市渝北区洪湖西路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