一种基于核心论元的篇章级事件抽取方法

doi:10.6040/j.issn.1671-9352.1.2023.080

摘要/Abstract

摘要：

提出一种基于核心论元的篇章级事件抽取选取方法(core arguments-based document level event extraction, CA-DocEE)，该方法根据论元在篇章级事件中的分布特点定义核心论元的选取标准，采用异质图卷积神经网络将篇章上下文信息用于增强论元实体编码，基于机器阅读理解方法捕捉句子中的深层次语义信息来进行论元角色分类。在篇章级事件抽取公开数据集上，本文提出的方法的微平均F1值达到了80.1%，取得了与目前已知最好方法相当的效果。

关键词: 事件抽取, 篇章级事件抽取, 机器阅读理解, 图卷积神经网络

Abstract:

A document-level event extraction method based on core arguments(CA-DocEE) is proposed, which defines criteria for selecting core arguments based on their distributions in document-level events, uses heterogeneous graph convolutional neural networks to augment document contextual information for encoding argument entities, and captures deep semantic information in sentences based on machine reading comprehension methods for classifying the role of arguments. On the document-level event extraction dataset, the method proposed in this paper achieves a micro-average F1 value of 80.1%, which is comparable with the state-of-the-art methods.

Key words: event extraction, document-level event extraction, machine reading comprehension, graph convolutional neural network

中图分类号:

TP391.1

孙承杰,李宗蔚,单丽莉,林磊. 一种基于核心论元的篇章级事件抽取方法[J]. 《山东大学学报(理学版)》, 2024, 59(7): 53-63.

Chengjie SUN,Zongwei LI,Lili SHAN,Lei LIN. A document-level event extraction method based on core arguments[J]. JOURNAL OF SHANDONG UNIVERSITY(NATURAL SCIENCE), 2024, 59(7): 53-63.

图/表 6

图1

图2

图3

表1

表2

表3

参考文献 26

1	ZHU Tong, QU Xiaoye, CHEN Wenliang, et al. Efficient document-level event extraction via pseudo-trigger-aware pruned complete graph[EB/OL]. (2021-12-11)[2023-10-18]. http://arxiv.org/abs/2112.06013.
2	RILOFF E. Automatically constructing a dictionary for information extraction tasks[C]//AAAI'93: Proceedings of the Eleventh National Conference on Artificial Intelligence. Washington: AAAI Press, 1993: 811-816.
3	AHN D. The stages of event extraction[C]// Proceedings of the Workshop on Annotating and Reasoning about Time and Events. Stroudsburg: Association for Computational Linguistics, 2006: 1-8.
4	CHEN Zheng, JI Heng. Language specific issue and feature exploration in Chinese event extraction[C]//Proceedings of Human Language Technologies: the 2009 Annual Conference of the North American Chapter of the Association for Computational Linguistics, Companion Volume: Short Papers on-NAACL'09. Morristown: Association for Computational Linguistics, 2009: 209-212.
5	LIAO S S, GRISHMAN R. Using document level cross-event inference to improve event extraction[C]//Proceedings of the 48th Annual Meeting of the Association for Computational Linguistics. Uppsala: ACM, 2010: 789-797.
6	JI H, GRISHMAN R. Refining event extraction through cross-document inference[C]//Proceedings of ACL-08: Hlt. Columbus: Association for Computational Linguistics, 2008: 254-262.
7	CHEN Yubo, XU Liheng, LIU Kang, 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. Beijing: Association for Computational Linguistics, 2015: 167-176.
8	YANG Sen, FENG Dawei, QIAO Linbo, 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: Association for Computational Linguistics, 2019: 5284-5294.
9	SHA L, LIU J, LIN C Y, et al. RBPB: regularization-based pattern balancing method for event extraction[C]//Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics. Berlin: Association for Computational Linguistics, 2016: 1224-1234.
10	DU X Y, CLAIRE C. Event extraction by answering (almost) natural questions[EB/OL]. (2020-04-28)[2023-10-18]. http://arxiv.org/abs/2004.13625.
11	CHEN C, NG V. Joint modeling for Chinese event extraction with rich linguistic features[C]// Proceedings of COLING. Mumbai: The COLING 2012 Organizing Committee, 2012: 529-544.
12	LI Qi, JI Heng, HUANG Liang, et al. Joint event extraction via structured prediction with global features[C]// Proceedings of the 51st Annual Meeting of the Association for Computational Linguistics. Bulgaria: Association for Computational Linguistics, 2013: 73-82.
13	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. San Diego: Association for Computational Linguistics, 2016: 300-309.
14	CHEN Yubo, LIU Shulin, ZHANG Xiang, et al. Automatically labeled data generation for large scale event extraction[C]// Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics. Vancouver: Association for Computational Linguistics, 2017: 409-419.
15	LI Qian , PENG Hao , LI Jianxin , et al. Reinforcement learning-based dialogue guided event extraction to exploit argument relations[J]. IEEE/ACM Transactions on Audio, Speech, and Language Processing, 2022, 30, 520- 533. doi: 10.1109/TASLP.2021.3138670
16	YANG Hang, CHEN Yubo, LIU Kang, et al. DCFEE: a document-level Chinese financial event extraction system based on automatically labeled training data[C]// Proceedings of ACL 2018, System Demonstrations. Melbourne: Association for Computational Linguistics, 2018: 50-55.
17	WANG Haitao , ZHU Tong , WANG Mingtao , et al. A prior information enhanced extraction framework for document-level financial event extraction[J]. Data Intelligence, 2021, 3 (3): 460- 476. doi: 10.1162/dint_a_00103
18	ZHANG Hongkuan, SONG Hui, WANG Shuyi, et al. A bert-based end-to-end model for Chinese document-level event extraction[C]// Proceedings of the 19th Chinese National Conference on Computational Linguistics. Haikou: Chinese Information Processing Society of China, 2020: 390-401.
19	YANG Hang, SUI Dianbo, CHEN Yubo, et al. Document-level event extraction via parallel prediction networks[C]//Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing. Stroudsburg: Association for Computational Linguistics, 2021: 6298-6308.
20	WANG Peng , DENG Zhenkai , CUI Ruilong . TDJEE: a document-level joint model for financial event extraction[J]. Electronics, 2021, 10 (7): 824. doi: 10.3390/electronics10070824
21	LIU Jian , LIANG Chen , XU Jinan . Document-level event argument extraction with self-augmentation and a cross-domain joint training mechanism[J]. Knowledge-based Systems, 2022, 257, 109904. doi: 10.1016/j.knosys.2022.109904
22	ZHENG Shun, CAO Wei, XU Wei, et al. Doc2EDAG: an end-to-end document-level framework for Chinese financial event extraction[C]//Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP). Hong Kong: Association for Computational Linguistics, 2019: 337-346.
23	XU Runxin, LIU Tianyu, LI Lei, et al. Document-level event extraction via heterogeneous graph-based interaction model with a tracker[C]//Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing. Stroudsburg: Association for Computational Linguistics, 2021: 3533-3546.
24	WEI Tianwen, QI Jianwei, HE Shenghuan, et al. Masked conditional random fields for sequence labeling[C]//Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. Stroudsburg: Association for Computational Linguistics, 2021: 2024-2035.
25	ZENG Shuang, XU Runxin, CHANG Baobao, et al. Double graph based reasoning for document-level relation extraction[C]// Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP). Stroudsburg: Association for Computational Linguistics, 2020: 1630-1640.
26	WANG Difeng, HU Wei, CAO Ermei, et al. Global-to-local neural networks for document-level relation extraction[C]// Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP). Stroudsburg: Association for Computational Linguistics, 2020: 3711-3721.

多维度评价

Viewed

Full text

Abstract

Cited

Shared

Discussed

论元提及识别模型	micro-P	micro-R	micro-F1
BiLSTM+CRF	88.0	82.9	85.4
BERT+MCRF	91.0	91.2	91.1

模型	S	M	All
DCFEE-O	72.4	52.4	63.2
GIT	86.8	72.3	79.9
PTPCG	88.2	69.1	79.4
PTPCG复现结果	86.2	68.6	78.5
CA-DocEE	88.0	70.3	80.1

模型	micro-P	micro-R	micro-F1
使用Zhu^[1]的伪触发词作为核心论元	82.7	76.8	79.6
-MRC	83.2	76.9	79.9
CA-DocEE	83.7	77.4	80.1

[1]	鲍亮,陈志豪,陈文章,叶锴,廖祥文. 基于双重多路注意力匹配的观点型阅读理解[J]. 《山东大学学报(理学版)》, 2021, 56(3): 44-53.
[2]	阴爱英,林建洲,吴运兵,廖祥文. 融合图卷积神经网络的文本情感分类[J]. 《山东大学学报(理学版)》, 2021, 56(11): 15-23.
[3]	林丽. 基于核心依存图的新闻事件抽取[J]. 山东大学学报（理学版）, 2016, 51(9): 121-126.
[4]	李风环, 郑德权, 赵铁军. 基于浅层语义分析的主题事件的时间识别[J]. 山东大学学报（理学版）, 2015, 50(11): 74-80.
[5]	徐霞, 李培峰, 郑新, 朱巧明. 面向半监督中文事件抽取的事件推理方法[J]. 山东大学学报（理学版）, 2014, 49(12): 12-17.