基于组合神经网络的中文事件抽取

doi:10.12066/j.issn.1007-2861.2223

上海大学学报(自然科学版) ›› 2021, Vol. 27 ›› Issue (3): 535-543.doi: 10.12066/j.issn.1007-2861.2223

基于组合神经网络的中文事件抽取

季忠祥, 吴悦()

上海大学计算机工程与科学学院, 上海 200444

收稿日期:2020-02-23 出版日期:2021-06-30 发布日期:2021-06-27
通讯作者: 吴悦 E-mail:ywu@shu.edu.cn
作者简介:吴悦(1960—), 女, 教授, 博士生导师, 博士, 研究方向为自然语言处理. E-mail: ywu@shu.edu.cn

Event extraction of Chinese text based on composite neural network

JI Zhongxiang, WU Yue()

School of Computer Engineering and Science, Shanghai University, Shanghai 200444, China

Received:2020-02-23 Online:2021-06-30 Published:2021-06-27
Contact: WU Yue E-mail:ywu@shu.edu.cn

摘要/Abstract

摘要：

中文事件抽取通常使用循环神经网络(recurrent neural network, RNN)来进行事件和事件要素的抽取, 但 RNN 在处理长度较长的词语时容易丢失重要信息, 为此提出一种组合卷积神经网络(convolutional neural network, CNN)与双向长短期记忆(bidirectional long short-term memory, Bi-LSTM)网络的中文事件抽取模型 CNN-Bi-LSTM-CRF, 其中 CRF (conditional random field) 为条件随机场. 采用基于注意力机制和语义特征生成的字词联合向量, 使用 CNN 和 Bi-LSTM 模型对字词联合向量进行处理, 以获取其隐含表示, 最后通过 CRF 得出预测结果. 实验结果表明, 所提出的方法与其他现有的中文事件抽取方法相比, 准确率有明显提升.

关键词: 事件抽取, 卷积神经网络, 长短期记忆

Abstract:

The recurrent neural network is widely used in the event extraction of Chinese text to extract events and event elements, but it usually loses essential information when processing long words. In this study, the convolutional neural network (CNN) and the bidirectional long short-term memory (Bi-LSTM) network were combined to develop a novel event extraction model known as CNN-Bi-LSTM-conditional random field (CRF). A joint vector of characters and words was adopted based on the attention mechanism and semantic features, and the CNN and Bi-LSTM models were used to process the vector to obtain its implicit representation. Finally, the CRF was used to obtain the prediction results. The experimental results show that the proposed method is more accurate than other existing event extraction methods in extracting Chinese text.

Key words: event extraction, convolutional neural network, long short-term memory

中图分类号:

TP391.1

季忠祥, 吴悦. 基于组合神经网络的中文事件抽取[J]. 上海大学学报(自然科学版), 2021, 27(3): 535-543.

JI Zhongxiang, WU Yue. Event extraction of Chinese text based on composite neural network[J]. Journal of Shanghai University（Natural Science Edition）, 2021, 27(3): 535-543.

图/表 9

表1

图1

图2

图3

图4

表2

表3

表4

表5

参考文献 14

[1]	Doddington G, Mitchell A, Przybocki M, et al. The automatic content extraction (ACE) program-tasks, data, and evaluation[C]// Proceedings of the Fourth International Conference on Language Resources and Evaluation. 2004: 837-840.
[2]	Consortium L D. ACE (automatic content extraction) Chinese annotation guidelines for events [EB/OL]. [2020-02-20]. http://www.ldc.upenn.edu/Projects/ACE.
[3]	罗明, 黄海量. 一种基于有限状态机的中文地址标准化方法[J]. 计算机应用研究, 2016,33(12):3691-3695.
	Luo M, Huang H L. New method of Chinese address standardization based on finite state machine theory[J]. Application Research of Computers, 2016,33(12):3691-3695.
[4]	Mohammed G H A Z, Can A B. ROLEX-SP: rules of lexical syntactic patterns for free text categorization[J]. Knowledge-Based Systems, 2011,24(1):58-65. doi: 10.1016/j.knosys.2010.07.005
[5]	刘丹丹, 彭成, 钱龙华, 等. 词汇语义信息对中文实体关系抽取影响的比较[J]. 计算机应用, 2012,32(8):2238-2244.
	Liu D D, Peng C, Qian L H, et al. Comparative analysis of impact of lexical semantic information on Chinese entity relation extraction[J]. Journal of Computer Applications, 2012,32(8):2238-2244. doi: 10.3724/SP.J.1087.2012.02238
[6]	Chieu H L, Ng H T. A maximum entropy approach to information extraction from semi-structured and free text[C]// Proceedings of the Eighteenth National Conference on Artificial Intelligence. 2002: 786-791.
[7]	Ahn D. The stages of event extraction[C]// Proceedings of the Workshop on Annotations and Reasoning about Time and Events. 2006: 1-8.
[8]	付剑锋, 刘宗田, 刘炜, 等. 基于特征加权的事件要素识别[J]. 计算机科学, 2010,37(3):239-241.
	Fu J F, Liu Z T, Liu W, et al. Feature weighting based event argument identification[J]. Computer Science, 2010,37(3):239-241.
[9]	Zeng Y, Yang H H, Feng Y S, et al. A convolution Bi-LSTM neural network model for Chinese event extraction[C]// Proceedings of International Conference on Computer Processing of Oriental Languages. 2016: 275-287.
[10]	张亚军, 刘宗田, 周文. 基于深度信念网络的事件识别[J]. 电子学报, 2017,45(6):1415-1423.
	Zhang Y J, Liu Z T, Zhou W. Event recognition based on deep belief network[J]. Acta Electronica Sinica, 2017,45(6):1415-1423.
[11]	Wu Y, Zhang J. Chinese event extraction based on attention and semantic features: a bidirectional circular neural network[J]. Future Internet, 2018,10(10):95-105. doi: 10.3390/fi10100095
[12]	Chen X, Xu L, Liu Z, et al. Joint learning of character and word embeddings[C]// Proceedings of the 24th International Conference on Artificial Intelligence. 2015: 1236-1242.
[13]	Misawa S, Taniguchi M, Miura Y, et al. Character-based bidirectional LSTM-CRF with words and characters for Japanese named entity recognition[C]// Proceedings of the First Workshop on Subword and Character Level Models in NLP. 2017: 97-102.
[14]	Sato M, Shindo H, Yamada I, et al. Segment-level neural conditional random fields for named entity recognition[C]// Proceedings of the Eighth International Joint Conference on Natural Language Processing. 2017: 97-102.

基于组合神经网络的中文事件抽取

Event extraction of Chinese text based on composite neural network

RichHTML

PDF

可视化

摘要/Abstract

引用本文

使用本文

图/表 9

参考文献 14

相关文章 4

编辑推荐

Metrics

本文评价

[1]	黄嘉宝, 朱永华, 周霁婷, 高文靖. 基于卷积神经网络的多肉植物细粒度图像分类[J]. 上海大学学报(自然科学版), 2020, 26(2): 283-291.
[2]	周敬一, 郭燕, 丁友东. 基于深度学习的中文影评情感分析[J]. 上海大学学报(自然科学版), 2018, 24(5): 703-712.
[3]	冉鹏, 王灵, 李昕, 刘鹏伟. 改进Softmax分类器的深度卷积神经网络及其在人脸识别中的应用[J]. 上海大学学报(自然科学版), 2018, 24(3): 352-366.
[4]	刘惠彬, 陈强, 吴飞, 赵毅. 基于卷积神经网络的固定群体中目标人物分类[J]. 上海大学学报(自然科学版), 2017, 23(6): 874-.