Cascade Type Event Extraction Model Based on Argument Association Graph

doi:10.19678/j.issn.1000-3428.0070456

Abstract

Abstract:

Event extraction is a crucial task in the field of information extraction that aims to identify and extract specific events or factual information from natural language texts. A key challenge in event extraction is event overlap, where a single word may act as a trigger for different event types or play varying roles across events. Existing methods for overlapping event extraction often fail to adequately consider the relationships between argument roles, which affect the event extraction performance. To address the nested event challenge in the event extraction domain, this study proposes a cascade type event extraction model called Argument Association Graph (AAG)-based Cascade Type Event Extraction model (AAGCTEE). AAGCTEE utilizes XLM-RoBERTa-base for deep encoding and enhances the representation between word pairs using conditional layer normalization and dilated convolution techniques. In the trigger recognition module, the AAGCTEE Cascade Type Predictor (CTP) accurately identifies triggers related to multiple event types, effectively solving the common issue of nested triggers in traditional event extraction. In the argument recognition and classification module, AAGCTEE employs an Argument Association Graph (AAG) and a Global Normalization Decoding (GND) strategy to efficiently handle complex nested argument structures. The average F1 values for Trigger Identification (TI), Trigger Classification (TC), Argument Identification (AI), and Argument Classification (AC) of AAGCTEE are higher than those of the comparative models by 4.12, 0.17, 13.66, and 0.98 percentage points for Chinese datasets DuEE and FewFC and English datasets PHEE and CASIE, respectively. Compared with the ablation experiments lacking CTP, AAG, and GND, AAGCTEE demonstrates an average increase of 5.56, 5.31, and 5.08 percentage points in the average F1 values across the four evaluation metrics, verifying its effectiveness in extracting complex events.

Key words: event extraction, Argument Association Graph (AAG), cascade type, overlapping event, Global Normalization Decoding (GND)

摘要：

事件抽取是信息抽取领域中的一项重要任务, 其目标是从自然语言文本中识别并提取出特定的事件或事实信息。事件重叠是事件抽取任务的一个关键问题, 即同一个词语可能充当不同事件类型的触发词或者在不同事件中扮演不同的角色。目前的重叠事件抽取方法往往未能充分考虑论元角色之间的关联关系, 这在一定程度上影响了事件抽取的效果。针对事件抽取领域的事件嵌套挑战, 提出一种基于论元关联图(AAG)的级联类型事件抽取模型(AAGCTEE)。AAGCTEE依托XLM-roberta-base实现深度编码, 并通过条件层归一化及空洞卷积技术优化词对间的表征。在触发词识别模块中, AAGCTEE的级联类型预测器(CTP)能够精准辨识多类事件相关的触发词, 有效解决了传统事件抽取中常见的触发词嵌套难题。在论元识别分类模块中, AAGCTEE借助AAG和全局归一化解码(GND)策略, 高效处理了复杂的嵌套论元结构。AAGCTEE的触发词识别(TI)、触发词分类(TC)、论元识别(AI)、论元分类(AC)的平均F1值在中文数据集DuEE、FewFC与英文数据集PHEE、CASIE上均表现出色, 分别比表现最佳的对比模型平均高4.12、0.17、13.66和0.98百分点。相较于去除CTP、AAG和GND的消融实验, AAGCTEE在上述4个任务的平均F1值上平均提高了5.56、5.31和5.08百分点, 验证了AAGCTEE在提取复杂事件方面的有效性。

关键词: 事件抽取, 论元关联图, 级联类型, 重叠事件, 全局归一化解码

RAO Dongning, MA Zhuowen. Cascade Type Event Extraction Model Based on Argument Association Graph[J]. Computer Engineering, 2026, 52(7): 121-130.

饶东宁, 马卓文. 基于论元关联图的级联类型事件抽取模型[J]. 计算机工程, 2026, 52(7): 121-130.

/ Recommend / Download Citations

URL: https://www.ecice06.com/EN/10.19678/j.issn.1000-3428.0070456

https://www.ecice06.com/EN/Y2026/V52/I7/121

Figures/Tables 14

Fig.1 An example of overlapping event

Fig.2 Cascade type event extraction model based on argument association graph

Fig.3 Diagram of dilated convolutional structure

Fig.4 An example of argument correlation diagram

References 29

1	王浩畅, 周郴莲, PETRESCUMarius Gabriel. 基于深度学习的事件抽取研究综述. 软件学报, 2023, 34(8): 3905- 3923. doi: 10.13328/j.cnki.jos.006645
	WANG H C, ZHOU C L, PETRESCU M G. Survey on event extraction based on deep learning. Journal of Software, 2023, 34(8): 3905- 3923. doi: 10.13328/j.cnki.jos.006645
2	LI Q, LI J X, SHENG J W, et al. A survey on deep learning event extraction: approaches and applications. IEEE Transactions on Neural Networks and Learning Systems, 2024, 35(5): 6301- 6321. doi: 10.1109/TNNLS.2022.3213168
3	万齐智, 万常选, 胡蓉, 等. 面向研究问题的深度学习事件抽取综述. 自动化学报, 2024, 50(11): 2079- 2101. doi: 10.16383/j.aas.c230184
	WAN Q Z, WAN C X, HU R, et al. A review of deep learning event extraction for research problems. Acta Automatica Sinica, 2024, 50(11): 2079- 2101. doi: 10.16383/j.aas.c230184
4	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. Florence, Italy: Association for Computational Linguistics, 2019: 5284-5294.
5	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. 计算机工程, 2024, 50(9): 63- 71. doi: 10.19678/j.issn.1000-3428.0068523
	QU X Y, LI B, WEN L Q. Research on event extraction for administrative law enforcement case texts. Computer Engineering, 2024, 50(9): 63- 71. doi: 10.19678/j.issn.1000-3428.0068523
6	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. Online: Association for Computational Linguistics, 2021: 164-174.
7	JIANG Z T, KONG F. PairEE: a novel pairing-scoring approach for better overlapping event extraction[M]//ILIADIS L, PAPALEONIDAS A, ANGELOV P. Artificial neural networks and machine learning—ICANN 2023. Berlin, Germany: Springer, 2023: 128-139.
8	CHEN X Y, ZHANG W W. LinkEE: linked list based event extraction with attention mechanism for overlapping events[M]//CHEN J, HUYNH V N, TANG X J. Knowledge and systems sciences. Berlin, Germany: Springer, 2023: 33-47.
9	刘泽旖, 余文华, 洪智勇, 等. 基于问题回答模式的中文事件抽取. 计算机工程与应用, 2023, 59(2): 153- 160. doi: 10.3778/j.issn.1002-8331.2107-0157
	LIU Z Y, YU W H, HONG Z Y, et al. Chinese event extraction using question answering. Computer Engineering and Applications, 2023, 59(2): 153- 160. doi: 10.3778/j.issn.1002-8331.2107-0157
10	陈泉林, 贾珺, 樊硕. 基于ABBSAC模型的中文事件抽取方法. 微电子学与计算机, 2024, 41(5): 57- 66. doi: 10.19304/J.ISSN1000-7180.2023.0292
	CHEN Q L, JIA J, FAN S. Chinese event extraction method based on ABBSAC model. Microelectronics & Computer, 2024, 41(5): 57- 66. doi: 10.19304/J.ISSN1000-7180.2023.0292
11	冯兴杰, 赵新阳, 冯小荣. 基于软参数共享的事件联合抽取方法. 计算机应用研究, 2023, 40(1): 91- 96. doi: 10.19734/j.issn.1001-3695.2022.06.0252
	FENG X J, ZHAO X Y, FENG X R. Joint event extraction method based on soft parameter sharing. Application Research of Computers, 2023, 40(1): 91- 96. doi: 10.19734/j.issn.1001-3695.2022.06.0252
12	纪婉婷, 马宇航, 鲁闻一, 等. 文档级事件抽取反向推理模型. 计算机工程与应用, 2024, 60(5): 122- 129. doi: 10.3778/j.issn.1002-8331.2210-0237
	JI W T, MA Y H, LU W Y, et al. Reverse inference model for document-level event extraction. Computer Engineering and Applications, 2024, 60(5): 122- 129. doi: 10.3778/j.issn.1002-8331.2210-0237
13	ZHONG Y Z, XU T, LUO P F. Contextualized hybrid prompt-tuning for generation-based event extraction[C]//Proceedings of the 16th International Conference on Knowledge Science, Engineering and Management. Berlin, Germany: Springer, 2023: 374-386.
14	王士浩, 王中卿, 李寿山, 等. 基于知识蒸馏与模型集成的事件论元抽取方法. 计算机工程, 2022, 48(7): 97- 103. doi: 10.19678/j.issn.1000-3428.0061790
	WANG S H, WANG Z Q, LI S S, et al. Event argument extraction method based on knowledge distillation and model ensemble. Computer Engineering, 2022, 48(7): 97- 103. doi: 10.19678/j.issn.1000-3428.0061790
15	严海宁, 余正涛, 黄于欣, 等. 融合词性语义扩展信息的事件检测模型. 计算机工程, 2024, 50(3): 89- 97. doi: 10.19678/j.issn.1000-3428.0066880
	YAN H N, YU Z T, HUANG Y X, et al. Event detection model integrating part of speech semantic extension information. Computer Engineering, 2024, 50(3): 89- 97. doi: 10.19678/j.issn.1000-3428.0066880
16	LU Y J, LIU Q, DAI D, et al. Unified structure generation for universal information extraction[C]//Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). Stroudsburg, USA: Association for Computational Linguistics, 2022: 5755-5772.
17	WANG X, ZHOU W K, ZU C, et al. InstructUIE: multi-task instruction tuning for unified information extraction[EB/OL]. [2024-08-10]. https://arxiv.org/abs/2304.08085.
18	WANG S J, YU M, CHANG S Y, et al. Query and extract: refining event extraction as type-oriented binary decoding[C]//Proceedings of the Findings of the Association for Computational Linguistics: ACL 2022. Dublin, Ireland: Association for Computational Linguistics, 2022: 169-182.
19	HSU I H, HUANG K H, ZHANG S N, et al. TAGPRIME: a unified framework for relational structure extraction[C]//Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). Toronto, Canada: Association for Computational Linguistics, 2023: 12917-12932.
20	HSU I H, HUANG K H, BOSCHEE E, et al. DEGREE: a data-efficient generation-based event extraction model[C]//Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. Stroudsburg, USA: Association for Computational Linguistics, 2022: 1890-1908.
21	CHOUDHARY M, DU X Y. QAEVENT: event extraction as question-answer pairs generation[C]//Proceedings of the Findings of the Association for Computational Linguistics: EACL 2024. Stroudsburg, USA: Association for Computational Linguistics, 2024: 1860-1873.
22	KAN Z G, PENG L W, QIAO L B, et al. Emancipating event extraction from the constraints of long-tailed distribution data utilizing large language models[C]//Proceedings of LREC-COLING 2024. Washington D. C., USA: IEEE Press, 2024: 5644-5653.
23	LI J W, FEI H, LIU J, et al. Unified named entity recognition as word-word relation classification. Proceedings of the AAAI Conference on Artificial Intelligence, 2022, 36(10): 10965- 10973. doi: 10.1609/aaai.v36i10.21344
24	YU F, KOLTUN V. Multi-scale context aggregation by dilated convolutions[EB/OL]. [2024-08-10]. http://arxiv.org/abs/1511.07122.
25	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[J]. Proceedings of the AAAI Conference on Artificial Intelligence, 2021, 35(16): 14638-14646.
26	LI X Y, LI F Y, PAN L, et al. DuEE: a large-scale dataset for Chinese event extraction in real-world scenarios[C]//ZHU X D, ZHANG M, HONG Y, et al. Natural language processing and Chinese computing. Berlin, Germany: Springer, 2020: 534-545.
27	SUN Z Y, LI J Z, PERGOLA G, et al. PHEE: a dataset for pharmacovigilance event extraction from text[C]//Proceedings of EMNLP 2022. Washington D. C., USA: IEEE Press, 2022: 5571-5587.
28	SATYAPANICH T, FERRARO F, FININ T. CASIE: extracting cybersecurity event information from text. Proceedings of the AAAI Conference on Artificial Intelligence, 2020, 34(5): 8749- 8757. doi: 10.1609/aaai.v34i05.6401
29	BROWN T B, MANN B, RYDER N, et al. Language models are few-shot learners[C]//Proceedings of the 34th International Conference on Neural Information Processing Systems. New York, USA: Curran Associates Inc., 2020: 1877-1901.

[1]	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.
[2]	QU Xiaoya, LI Bing, WEN Liqiang. Research on Event Extraction for Administrative Law Enforcement Case Texts [J]. Computer Engineering, 2024, 50(9): 63-71.
[3]	Hongpeng LI, Bo MA, Yating YANG, Lei WANG, Zhen WANG, Xiao LI. Document-level Event Extraction Method Based on Slot Semantic Enhanced Prompt Learning [J]. Computer Engineering, 2023, 49(9): 23-31.
[4]	YANG Hongju, JIN Xinyu. A General Model for Entity Relationship and Event Extraction [J]. Computer Engineering, 2023, 49(2): 143-149.
[5]	MIAO Jia, DUAN Yuexing, ZHANG Yueqin, ZHANG Zehua. Method for Extracting Event Trigger Words Based on the CNN-BiGRU Model [J]. Computer Engineering, 2021, 47(9): 69-74,83.
[6]	LIU Yiting, LI Peifeng. Event Trigger Extraction Based on Local Entity Characteristics [J]. Computer Engineering, 2019, 45(11): 213-217,224.
[7]	CHEN Bin,ZHOU Yong,LIU Bing. Event Trigger Word Extraction Based on Convolutional Bidirectional Long Short Term Memory Network [J]. Computer Engineering, 2019, 45(1): 153-158.
[8]	LIANG Yuexian,CHEN Ziyan,WANG Yang,ZHANG Yue,GUO Zhi. Bursty Event Detection Method Based on Spatio-temporal Analysis [J]. Computer Engineering, 2018, 44(5): 7-13.
[9]	HOU Li-Bin, LI Pei-Feng, SHU Qiao-Meng. Study of Event Recognition Based on CRFs and Cross-event [J]. Computer Engineering, 2012, 38(24): 191-195.

Please choose a citation manager

Content to export