基于事件感知记忆图增强的生成式事件抽取

Generative Event Extraction Based on Event-Aware Memory Graph Enhancement

摘要

针对生成式事件抽取模型在复杂场景下对触发词上下文建模不足、无法利用历史事件信息、难以捕捉复杂语义结构等问题,提出一种事件感知记忆图网络增强的生成式事件抽取模型.该模型通过事件感知注意力机制增强对触发词相关上下文的聚焦能力,利用动态事件记忆网络实现跨文本历史信息的复用,并借助事件图结构显式建模事件参数间的语义关联.在两个标准数据集上的实验结果表明,该模型在事件参数识别和分类任务上的性能均优于现有基线模型,可有效提升生成式模型在多事件和复杂语境场景下的抽取准确性和泛化能力.

Abstract

Aiming at the problems of insufficient modeling of trigger word contexts, inability to utilize historical event information, and difficulty in capturing complex semantic structures in generative event extraction models in complex scenarios, we proposed a generative event extraction model enhanced by event-aware memory graph network. The model enhanced its ability to focus on trigger word related contexts through an event-aware attention mechanism, utilized dynamic event memory network to achieve cross-text historical information reuse, and displayed semantic associations among modeling event arguments through an event graph structure. Experimental results on two standard datasets show that the proposed model outperforms existing baseline models in both event argument identification and classification tasks, effectively improving the extraction accuracy and generalization capability of generative models in multi-event and complex context scenarios.

关键词

生成式事件抽取 / 事件感知记忆图 / 动态事件记忆网络 / 注意力机制

Key words

generative event extraction / event-aware memory graph / dynamic event memory network / attention mechanism

参考文献

[1] Zhang W N, Zhao X Y, Zhao L, et al. DRL4IR: 2nd Workshop on Deep Reinforcement Learning for Information Retrieval[C]// Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval. New York: ACM, 2021: 2681-2684.

[2] Zhang H M, Liu X, Pan H J, et al. ASER: A Large-Scale Eventuality Knowledge Graph[C]// Proceedings of the Web Conference 2020. New York: ACM, 2020: 201-211.

[3] Han R J, Hsu I H, Sun J, et al. ESTER: A Machine Reading Comprehension Dataset for Reasoning about Event Semantic Relations[C]// Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing. [S. l.]: ACL, 2021: 7543-7559.

[4] Liang Y, Jiang Z X, Yin D, et al. RAAT: Relation-Augmented Attention Transformer for Relation Modeling in Document-Level Event Extraction[C]// Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. [S. l.]: ACL, 2022: 4985-4997.

[5] 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. [S. l.]: ACL, 2020: 7871-7880.

[6] Raffel C, Shazeer N, Roberts A, et al. Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer[J]. Journal of Machine Learning Research, 2020, 21(140): 1-67.

[7] Li Q, Ji H, Huang L. Joint Event Extraction via Structured Prediction with Global Features[C]// Proceedings of the 51st Annual Meeting of the Association for Computational Linguistics. [S. l.]: ACL, 2013: 73-82.

[8] 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. [S. l.]: ACL, 2015: 167-176.

[9] Nguyen T H, Cho K, Grishman R. Joint Event Extraction via Recurrent Neural Networks[C]// Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. [S. l.]: ACL, 2016: 300-309.

[10] Lu Y J, Lin H Y, Xu J, et al. Text2Event: Controllable Sequence-to-Structure Generation for End-to-end Event Extraction[C]// Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing. [S. l.]: ACL, 2021: 2795-2806.

[11] Hsu I H, Huang K H, Boschee E, et al. DEGREE: A Data-Efficient Generative Event Extraction Model[C]// Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. [S. l.]: ACL, 2022: 997-1008.

[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. [S. l.]: ACL, 2020: 671-683.

[13] Yuan J L. Learning Context-Aware Representation for Event Detection[C]// 2021 17th International Conference on Computational Intelligence and Security. Piscatahay, NJ: IEEE, 2021: 600-603.

[14] 胡蓉, 万常选, 万齐智, 等. 基于深度学习的篇章级事件抽取综述[J]. 计算机学报, 2025, 48(2):381-406.

[15] (Hu R, Wan C X, Wan Q Z, et al. A Survey of Discourse-Level Event Extraction Based on Deep Learning[J]. Journal of Computer Research and Development, 2025, 48(2):381-406.)

[16] Wang W Z, Dong L, Cheng H, et al. Augmenting Language Models with Long-Term Memory[J]. Advances in Neural Information Processing Systems, 2023, 36: 74530-74543.

[17] Du J L, Liu G R, Gao J, et al. Graph Neural Network-Based Entity Extraction and Relationship Reasoning in Complex Knowledge Graphs[EB/OL]. (2024-11-19)[2025-03-10]. https://arxiv.org/abs/2411.15195v1.

[18] Doddington G R, Mitchell A, Przybocki M A, et al. The Automatic Content Extraction (ACE) Program-Tasks, Data, and Evaluation[C]// Proceeding of the Fourth International Conterence on Language Resources and Evaluation. [S. l.]: ACL, 2004: 837-840.

[19] Song Z Y, Bies A, Strassel S, et al. From Light to Rich ERE: Annotation of Entities, Relations, and Events[C]// Proceedings of the 3rd Workshop on EVENTS: Definition, Detection, Coreference, and Representation. [S. l.]: ACL, 2015: 89-98.

[20] Wadden D, Wennberg U, Luan Y, et al. Entity, Relation, and Event Extraction with Contextualized Span Representations[C]// Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing. [S. l.]: ACL, 2019: 5784-5789.

[21] 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. [S. l.]: ACL, 2020: 7999-8009.

[22] Paolini G, Athiwaratkun B, Krone J, et al. Structured Prediction as Translation between Augmented Natural Languages[EB/OL]. (2021-01-14)[2025-05-12]. https://arxiv.org/abs/2101.05779.

[23] Li S, Ji H, Han J W. Document-Level Event Argument Extraction by Conditional Generation[C]// 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. [S. l.]: ACL, 2021: 894-908.

[24] Ma Y B, Wang Z H, Cao Y X, 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. [S. l.]: ACL, 2022: 6759-6774.

[25] Kruskal W H, Wallis W A. Use of Ranks in One-Criterion Variance Analysis[J]. Journal of the American statistical Association, 1952, 47(260): 583-621.

基金资助

国网浙江电力开发实施项目(7411HZ23000K)