动态异构图增强的级联解码事件抽取

doi:10.19678/j.issn.1000-3428.0069347

摘要/Abstract

摘要：

事件抽取是一项重要的信息抽取任务，旨在从自然语言文本中抽取出特定的事件或事实信息。在现实事件抽取场景中存在大量的事件重叠问题，即一个单词可以同时作为不同事件类型的触发词或不同角色的事件论元。然而，现有重叠事件抽取方法忽略了事件类型、论元角色等事件元素之间的关联和依赖关系，导致重叠事件抽取性能不佳。针对此问题，提出一种动态异构图增强的级联解码事件抽取模型DHG-EE，通过多粒度级联解码结构与领域-事件类型-论元角色异构图网络，有效实现重叠事件的结构表示与事件元素间的信息传递。具体来说：首先采用预训练模型对自然语言文本进行编码并构建由领域、事件类型和论元角色组成的多粒度异构图网络，将重叠事件论元与对应的多个领域节点和事件类型节点分开，并通过异构图的动态点边结构高效表示重叠事件的复杂关联关系；然后多粒度级联解码结构按照语义粒度由粗到细依次解码领域属性、事件类型、事件触发词和事件论元，并将上一粒度信息作为额外信息辅助下一粒度的解码，通过粗粒度领域和事件类型的预解码，有效约束了细粒度重叠触发词和事件论元的解码。实验结果表明，该模型在FewFC和DuEE1.0基准事件抽取数据集上的F1值优于对比的基线模型。

关键词: 信息抽取, 事件抽取, 重叠事件, 异构图网络, 级联解码

Abstract:

Event extraction is an important information extraction task that aims to extract specific events or information from natural language texts. There are many overlapping event problems, where one word is used as a trigger for different event types or when event arguments for different roles in real-life event extraction scenarios. However, existing overlapping event extraction methods ignore the correlations and dependencies between event elements, such as event types and argument roles, resulting in a poor performance of overlapping event extraction. To solve this problem, this paper proposes an event extraction model via cascade decoding enhanced by dynamic heterogeneous graphs, named DHG-EE, which can effectively realize the structural representation of overlapping events and facilitates information transmission between event elements through a multi-granularity cascade decoding structure and a domain-event type-argument role heterogeneous graph network. First, the pre-trained model encodes the natural language text and constructs a multi-granularity heterogeneous graph network composed of domains, event types, and argument roles, which separates the overlapping event arguments from the corresponding multiple domain nodes and event-type nodes and efficiently represents the complex associations of overlapping events through the dynamic point-edge structure of the heterogeneous graph. Then, the multi-granularity cascading decoding structure decodes domain attributes, event types, event trigger words, and event arguments, in order from coarse to fine, according to semantic granularity and uses the information of the previous granularity as additional information to assist in the decoding of the next granularity. Experimental results show that the F1 value of the proposed model is better than that of the baseline models on the FewFC and DuEE1.0 benchmark event extraction datasets.

Key words: information extraction, event extraction, overlapping event, heterogeneous graph network, cascade decoding

郭新宇, 马博, 艾比布拉·阿塔伍拉, 杨奉毅, 周喜. 动态异构图增强的级联解码事件抽取[J]. 计算机工程, 2025, 51(9): 91-100.

GUO Xinyu, MA Bo, Aibibula Atawula, YANG Fengyi, ZHOU Xi. Event Extraction via Cascade Decoding Enhanced by Dynamic Heterogeneous Graphs[J]. Computer Engineering, 2025, 51(9): 91-100.

https://www.ecice06.com/CN/Y2025/V51/I9/91

图/表 10

图1 重叠事件案例

Fig.1 Overlapping event cases

图2 模型总体框架

Fig.2 Overall model framework

图3 异构图网络层数在FewFC数据集上的F1值实验对比

Fig.3 Experimental comparison of F1 values of different layers in heterogeneous graph networks on the FewFC dataset

参考文献 27

1	CHEN Y B, XU L H, LIU K, et al. Event extraction via dynamic multi-pooling convolutional neural networks[C]//Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing (Volume 1: Long Papers). Stroudsburg, USA: ACL Press, 2015: 167-176.
2	YANG S, FENG D W, QIAO L B, et al. Exploring pre-trained language models for event extraction and generation[C]//Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics. Stroudsburg, USA: ACL Press, 2019: 5284-5294.
3	闻克妍, 纪婉婷, 宋宝燕. 融合局部上下文的双图文档级关系抽取方法. 小型微型计算机系统, 2025, 46 (3): 535- 541.
	WEN K Y , JI W T , SONG B Y . Bi-graph-based document-level relation extraction with local context fusion. Journal of Chinese Computer Systems, 2025, 46 (3): 535- 541.
4	XU N, XIE H H, ZHAO D Y. A novel joint framework for multiple Chinese events extraction[C]// Proceedings of the 19th Chinese National Conference on Computational Linguistics. Berlin, Germany: Springer, 2020: 174-183.
5	SHENG J W, GUO S, YU B W, et al. CasEE: a joint learning framework with cascade decoding for overlapping event extraction[C]//Proceedings of the Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021. Stroudsburg, USA: ACL Press, 2021: 164-174.
6	CAO H, LI J Y, SU F F, et al. OneEE: a one-stage framework for fast overlapping and nested event extraction[C]//Proceedings of the 29th International Conference on Computational Linguistics. Gyeongju, Republic of Korea: International Committee on Computational Linguistics, 2022: 1953-1964.
7	NGUYEN T M, NGUYEN T H. One for all: neural joint modeling of entities and events[C]//Proceedings of the AAAI Conference on Artificial Intelligence. Palo Alto, USA: AAAI Press, 2019: 6851-6858.
8	LIU X, LUO Z C, HUANG H Y. Jointly multiple events extraction via attention-based graph information aggregation[C]//Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing. Stroudsburg, USA: ACL Press, 2018: 1247-1256.
9	SHA L, QIAN F, CHANG B B, et al. Jointly extracting event triggers and arguments by dependency-bridge RNN and tensor-based argument interaction[C]//Proceedings of the AAAI Conference on Artificial Intelligence. Palo Alto, USA: AAAI Press, 2018: 5916-5923.
10	LUO Y, ZHAO H. Bipartite flat-graph network for nested named entity recognition[C]//Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics. Stroudsburg, USA: ACL Press, 2020: 6408-6418.
11	KIPF T N, WELLING M. Semi-supervised classification with graph convolutional networks[EB/OL]. [2024-01-05]. https://arxiv.org/abs/1609.02907v4.
12	VASWWANI A, SHAZEER N, PARMAR N, et al. Attention is all you need[C]//Proceedings of the 31st International Conference on Neural Information Processing Systems. Cambridge: MIT Press, 2017: 6000-6010.
13	ZAREMBA W, SUTSKEVER I, VINYALS O. Recurrent neural network regularization[EB/OL]. [2024-01-05]. https://arxiv.org/abs/1409.2329.
14	WALKER C , STRASSEL S , MEDERO J , et al. ACE 2005 multilingual training corpus. Progress of Theoretical Physics Supplements, 2006, 110, 261- 276.
15	DEVLIN J, CHANG M W, LEE K, et al. BERT: pre-training of deep 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. Stroudsburg, USA: ACL Press, 2019: 4171-4186.
16	张强, 曾俊玮, 陈锐. 基于对比学习与梯度惩罚的实体关系联合抽取模型. 吉林大学学报(理学版), 2024, 62 (5): 1155- 1162.
	ZHANG Q , ZENG J W , CHEN R . Entity-relation joint extraction model based on contrastive learning and gradient penalty. Journal of Jilin University (Science Edition), 2024, 62 (5): 1155- 1162.
17	HAMILTON W L, YING R, LESKOVEC J. Inductive representation learning on large graphs[C]//Proceedings of the 31st International Conference on Neural Information Processing Systems. Cambridge, USA: MIT Press, 2017: 1025-1035.
18	苏剑林. 基于Conditional Layer Normalization的条件文本生成[EB/OL]. [2024-01-05]. https://spaces.ac.cn/archives/7124#how_to_cite.
	SU J L. Conditional text generation based on conditional layer normalization[EB/OL]. [2024-01-05]. https://spaces.ac.cn/archives/7124#how_to_cite. (in Chinese)
19	MA Y D, LIU Q, QUAN Z B. Automated image segmentation using improved PCNN model based on cross-entropy[C]//Proceedings of 2004 International Symposium on Intelligent Multimedia, Video and Speech Processing. Washington D.C., USA: IEEE Press, 2004: 743-746.
20	KINGMA D P, BA J L. Adam: a method for stochastic optimization[EB/OL]. [2024-01-05]. https://arxiv.org/abs/1412.6980.
21	ZHOU Y, CHEN Y B, ZHAO J, et al. What the role is vs. what plays the role: semi-supervised event argument extraction via dual question answering[C]//Proceedings of the AAAI Conference on Artificial Intelligence. Palo Alto, USA: AAAI Press, 2021: 14638-14646.
22	LI X Y , LI F Y , PAN L , et al. DuEE: a large-scale dataset for Chinese event extraction in real-world scenarios. Berlin, Germany: Springer, 2020.
23	WOLF T, DEBUT L, SANH V, et al. Transformers: state-of-the-art natural language processing[C]//Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing: System Demonstrations. Stroudsburg, USA: ACL Press, 2020: 38-45.
24	DU X Y, CARDIE C. Document-level event role filler extraction using multi-granularity contextualized encoding[C]//Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics. Stroudsburg, USA: ACL Press, 2020: 8010-8020.
25	LAFFERTY J D, MCCALLUM A, PEREIRA F C N. Conditional random fields: probabilistic models for segmenting and labeling sequence data[C]//Proceedings of the 18th International Conference on Machine Learning. New York, USA: ACM Press, 2001: 282-289.
26	ZHENG S C, WANG F, BAO H Y, et al. Joint extraction of entities and relations based on a novel tagging scheme[C]//Proceedings of the 55th Annual Meeting of the Association forComputational Linguistics (Volume 1: Long Papers). Stroudsburg, USA: ACL Press, 2017: 1227-1236.
27	LI F Y, PENG W H, CHEN Y G, et al. Event extraction as multi-turn question answering[C]//Proceedings of the Findings of the Association for Computational Linguistics: EMNLP 2020. Stroudsburg, USA: ACL Press, 2020: 829-838.

[1]	杨冬菊, 黄俊涛. 基于大语言模型的中文科技文献标注方法[J]. 计算机工程, 2024, 50(9): 113-120.
[2]	屈潇雅, 李兵, 温立强. 面向行政执法案件文本的事件抽取研究[J]. 计算机工程, 2024, 50(9): 63-71.
[3]	曹渝昆, 程宇, 何祯奕, 徐康乐, 颜家洛, 李云峰. 文档上下文异构表示的句子级关系抽取方法[J]. 计算机工程, 2024, 50(5): 111-119.
[4]	李鸿鹏, 马博, 杨雅婷, 王磊, 王震, 李晓. 基于槽位语义增强提示学习的篇章级事件抽取方法[J]. 计算机工程, 2023, 49(9): 23-31.
[5]	衡红军, 苗菁. 语义与句法信息加强的二元标记实体关系联合抽取[J]. 计算机工程, 2023, 49(4): 77-84.
[6]	杨红菊, 靳新宇. 一个实体关系与事件抽取的通用模型[J]. 计算机工程, 2023, 49(2): 143-149.
[7]	张吉祥, 张祥森, 武长旭, 赵增顺. 知识图谱构建技术综述[J]. 计算机工程, 2022, 48(3): 23-37.
[8]	苗佳, 段跃兴, 张月琴, 张泽华. 基于CNN-BiGRU模型的事件触发词抽取方法[J]. 计算机工程, 2021, 47(9): 69-74,83.
[9]	张军莲, 张一帆, 汪鸣泉, 黄永健. 基于图卷积神经网络的中文实体关系联合抽取[J]. 计算机工程, 2021, 47(12): 103-111.
[10]	何阳宇, 晏雷, 易绵竹, 李宏欣. 融合CRF与规则的老挝语军事领域命名实体识别方法[J]. 计算机工程, 2020, 46(8): 297-304.
[11]	柳亦婷, 李培峰. 基于局部实体特征的事件触发词抽取[J]. 计算机工程, 2019, 45(11): 213-217,224.
[12]	陈斌,周勇,刘兵. 基于卷积双向长短期记忆网络的事件触发词抽取[J]. 计算机工程, 2019, 45(1): 153-158.
[13]	梁月仙,陈自岩,王洋,张跃,郭智. 基于时空分析的突发事件检测方法[J]. 计算机工程, 2018, 44(5): 7-13.
[14]	李雁群,何云琪,钱龙华,周国栋. 基于维基百科的中文嵌套命名实体识别语料库自动构建[J]. 计算机工程, 2018, 44(11): 76-82.
[15]	王辉,郁波,洪宇,肖仰华. 基于知识图谱的Web信息抽取系统[J]. 计算机工程, 2017, 43(6): 118-124.

选择文件类型/文献管理软件名称

选择包含的内容