融合事件类型的中文事件抽取方法

doi:10.3778/j.issn.1002-8331.2308-0440

摘要/Abstract

摘要： 事件抽取技术是自动化地从文本信息中获得结构性数据的重要手段，也是自然语言处理领域的重点研究方向之一。事件抽取包含两个子任务，事件类型检测与事件论元抽取。近年来的事件抽取研究引入了预训练语言模型作为文本的语义表征，然后采用序列标注BIO完成抽取任务，但此类方法容易存在标签歧义问题。因此又有学者提出在事件文本特征中融入特征知识以避免歧义，可现有的融合方法忽略了事件抽取各个子任务间的依赖关系。为解决以上问题，针对事件抽取任务采用联合学习的算法框架，通过门融合机制将事件类型信息作为新知识融入事件的文本表示中，再进行事件触发词抽取与事件论元抽取。实验结果证明该算法模型在论元抽取任务上较之基线方法表现更优异。

关键词: 文本事件抽取, 预训练语言模型, 门融合

Abstract: Event extraction is an essential task which aims to extract structural event information from unstructured text. Event extraction consists of two sub-tasks, event type detection and event argument extraction. Recent prior work introduced pre-trained language model to get semantic representation of the text. Some works formulate EE into a sequence labeling task (BIO), which is prone to label ambiguity. While others integrate feature knowledge into event text representation to avoid ambiguity. However, the existing methods of integration ignore the dependencies between each sub-task of event extraction. This paper proposes a joint learning method for the event extraction task. The event type feature is integrated into the text representation as new knowledge through gate fusion mechanism. Experimental results show that this method performs better than the baselines on event argument extraction.

Key words: text event extraction, pre-trained language model, gate fusion

王瑾睿, 李劼. 融合事件类型的中文事件抽取方法[J]. 计算机工程与应用, 2025, 61(1): 214-220.

WANG Jinrui, LI Jie. Gated Fusion Framework for Chinese Event Extraction[J]. Computer Engineering and Applications, 2025, 61(1): 214-220.

参考文献

[1] 王人玉, 项威, 王邦, 等. 文档级事件抽取研究综述[J]. 中文信息学报, 2023, 37(6): 1-14.
WANG R Y, XIANG W, WANG B, et al. Review of document-level event extraction research [J]. Journal of Chinese Information Processing, 2023, 37(6): 1-14.
[2]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, 2019: 4171-4186.
[3] DU X Y, CLAIRE 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, 2020: 8010-8020.
[4] 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 for Computational Linguistics, 2017: 1227-1236.
[5] 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, 2019: 5783-5788.
[6] LI F Y, PENG W H, CHEN Y G, et al. Event extraction as multi-turn question answering[C]//Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing: Findings, 2020: 829-838.
[7] CHEN Y M, CHEN T F, EBNER S, et al. Reading the manual: event extraction as definition comprehension[C]//Proceedings of the Fourth Workshop on Structured Prediction for NLP@EMNLP, 2020: 74-83.
[8] YANG S, FENG D W, QIAO L B, et al. Exploring pre-trained language models for event extraction and generation[C]//Proceedings of the Annual Meeting of the Association for Computational Linguistics, 2019: 5284-5294.
[9] MCCANN B, BRADBURY J, XIONG C M, et al. Learned in translation: contextualized word vectors[C]//Proceedings of the 31st International Conference on Neural Information Processing Systems, 2017: 6294-6305.
[10] PETERS M, NEUMANN M, IYYE R M, et al. Deep contextualized word representations[C]//Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, 2018: 2227-2237.
[11] HOCHREITER S, SCHMIDHUBER J. Long short-term memory[J]. Neural Computation, 1997, 9(8): 1735-1780.
[12] HOWARD J, RUDER S. Universal language model fine-tuning for text classification[C]//Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics, 2018: 328-339.
[13] ASHISH V, NOAM S, NIKI P, et al. Attention is all you need[C]//Proceedings of Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems, 2017: 5998-6008.
[14] ALEC R, KARTHIK N, TIM S, et al. Improving language understanding by generative pre-training[EB/OL]. [2023-05-21]. https://www.cs.ubc.ca/~amuham01/LING530/papers/ radford2018improving.pdf.
[15] LI Q Z, ZHANG Q. A unified model for financial event classification, detection and summarization[C]//Proceedings of International Joint Conference on Artificial Intelligence, 2020.
[16] LU Y, LIN H, XU J, et al. Text2Event: controllable sequence-to-structure generation for end-to-end event extraction[J]. arXiv:2106.09232, 2021.
[17] 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 Annual Meeting of the Association for Computational Linguistics, 2020: 164-174.
[18] YU B W, ZHANG Z Y, SHENG J W, et al. Semi-open information extraction[C]//Proceedings of the Web Conference, 2021.
[19] 王腾, 张大伟, 王利琴, 等. 多模态特征自适应融合的虚假新闻检测[J]. 计算机工程与应用, 2024, 60(13): 102-112.
WANG T, ZHANG D W, WANG L Q, et al. Multimodal feature adaptive fusion for fake news detection[J]. Computer Engineering and Applications, 2024, 60(13): 102-112.
[20] CHO K, VAN MERRIENBOER B, GULCEHRE C, et al. Learning phrase representations using RNN encoder-decoder for statistical machine translation[C]//Proceedings of Association for Computational Linguistics, 2014.
[21] RUPESH K S, KLAUS G, JURGEN S, Training very deep networks[C]//Proceedings of Neural Information Processing Systems, 2015.
[22] XU D, OUYANG W L, WANG X G, et al. PAD-Net: multi-tasks guided prediction-and-distillation network for simultaneous depth estimation and scene parsing[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, 2018.
[23] KONG S, FOWLKES C. Recurrent scene parsing with perspective understanding in the loop[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2018.
[24] LI X T, ZHAO H, HAN L, et al. GFF: gated fully fusion for semantic segmentation[C]//Proceedings of Association for the Advance of Artificial Intelligence, 2020.
[25] 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, 2013: 73-82.
[26] LIU S L, LI Y, ZHANG F, et al. Event detection without triggers[C]//Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, 2019: 735-744.
[27] LI X Y, LI F Y, PAN L, et al. DuEE: a large-scale dataset for Chinese event extraction in real-world scenarios[C]//Proceedings of the CCF International Conference on Natural Language Processing and Chinese Computing, 2020.
[28] 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, 2021: 14638-14646.
[29] CHEN Y B, XU L H, LIU K, et al. Event extraction via dynamic multipooling convolutional neural networks[C]//Proceedings of the Annual Meeting of the Association for Computational Linguistics, 2015: 167-176.
[30] ZHANG Z Y, HAN X, LIU Z Y, et al. ERNIE: enhanced language representation with informative entities[C]//Proceedings of the Annual Meeting of the Association for Computational Linguistics, 2019.