Chemical Accident Classification Based on BLSTM-Attention Neural Network Model

doi:10.15888/j.cnki.csa.007619

AIPUB归智期刊联盟

WeChat

Mobile website

2025-4-25- 14

Home > Archive>Volume 29, Issue 10, 2020 >205-210. DOI:10.15888/j.cnki.csa.007619

PDF HTML XML Export Cite reminder

Chemical Accident Classification Based on BLSTM-Attention Neural Network Model
DOI:
                        10.15888/j.cnki.csa.007619
                    
CSTR:
                        [cstr]
                    
Author:
                        GE YanGE Yan
College of Information Science and Technology, Qingdao University of Science and Technology, Qingdao 266061, China
Find this author on All Journals
Find this author on BaiDu
Search for this author on this site
ZHENG Li-JieZHENG Li-Jie
College of Information Science and Technology, Qingdao University of Science and Technology, Qingdao 266061, China
Find this author on All Journals
Find this author on BaiDu
Search for this author on this site
DU Jun-WeiDU Jun-Wei
College of Information Science and Technology, Qingdao University of Science and Technology, Qingdao 266061, China
Find this author on All Journals
Find this author on BaiDu
Search for this author on this site
CHEN ZhuoCHEN Zhuo
College of Information Science and Technology, Qingdao University of Science and Technology, Qingdao 266061, China
Find this author on All Journals
Find this author on BaiDu
Search for this author on this site

                    
Affiliation:
Clc Number:
Fund Project:

Article

Figures

Metrics

Reference [17]

Cited by

Materials

Comments

Abstract:

Chemical accident news data contains information such as news content, titles, and news sources. The text of news content is highly dependent on the context. In order to extract text features more accurately and improve the accuracy of chemical accident classification, this study proposes a Bidirectional LSTM (BLSTM-Attention) neural network model based on Attention mechanism to extract features of chemical news texts and realize text classification. The BLSTM-Attention neural network model can combine text context semantic information to extract text features of accident news through forward and reverse angles. Considering that different words have different contributions to the text in the accident news, the Attention mechanism is added to assign different weights to different words and sentences. Finally, the proposed classification method is compared with Naive-Bayes, CNN, RNN, BLSTM classification method on the same chemical accident news data set. Experimental results show that the BLSTM-Attention neural network model proposed in this study is better than other classification models in chemical data set.

Key words:news of chemical accidents;feature extraction;BLSTM-Attention;text classification

Reference

[1] 曹赵娅. 我国化工行业发展的现状分析. 中国化工贸易, 2015, 7(25): 47. [doi: 10.3969/j.issn.1674-5167.2015.25.030

[2] 张志强. 基于自学习向量空间模型文本分类算法的研究与应用. 软件, 2016, 37(9): 118-121. [doi: 10.3969/j.issn.1003-6970.2016.09.028

[3] 罗慧钦, 陆向艳, 张雄宝, 等. 基于隐朴素贝叶斯的商品评论情感分类方法. 计算机工程与设计, 2017, 38(1): 203-208

[4] Kim Y. Convolutional neural networks for sentence classification. arXiv: 1408.5882, 2014.

[5] Zhang X, Zhao JB, LeCun Y. Character-level convolutional networks for text classification. arXiv: 1509.01626, 2015.

[6] 刘婷婷, 朱文东, 刘广一. 基于深度学习的文本分类研究进展. 电力信息与通信技术, 2018, 16(3): 1-7

[7] Auli M, Galley M, Quirk C, et al. Joint language and translation modeling with recurrent neural networks. Proceedings of 2013 Conference on Empirical Methods in Natural Language Processing. Washington, DC, USA. 2013. 1044-1054.

[8] 邵良杉, 周玉. 基于语义规则与RNN模型的在线评论情感分类研究. 中文信息学报, 2019, 33(6): 124-131. [doi: 10.3969/j.issn.1003-0077.2019.06.018

[9] 刘峰, 高赛, 于碧辉, 等. 基于Multi-head Attention和Bi-LSTM的实体关系分类. 计算机系统应用, 2019, 28(6): 118-124. [doi: 10.15888/j.cnki.csa.006944

[10] Nguyen HT, Le Nguyen M. An ensemble method with sentiment features and clustering support. Neurocomputing, 2019, 370: 155-165. [doi: 10.1016/j.neucom.2019.08.071

[11] 蓝雯飞, 徐蔚, 汪敦志, 等. 基于LSTM-Attention的中文新闻文本分类. 中南民族大学学报(自然科学版), 2018, 37(3): 129-133

[12] 万圣贤, 兰艳艳, 郭嘉丰, 等. 用于文本分类的局部化双向长短时记忆. 中文信息学报, 2017, 31(3): 62-68

[13] 高成亮, 徐华, 高凯. 结合词性信息的基于注意力机制的双向LSTM的中文文本分类. 河北科技大学学报, 2018, 39(5): 447-454. [doi: 10.7535/hbkd.2018yx05010

[14] 彭敏, 杨绍雄, 朱佳晖. 基于双向LSTM语义强化的主题建模. 中文信息学报, 2018, 32(4): 40-49. [doi: 10.3969/j.issn.1003-0077.2018.04.005

[15] Vaswani A, Shazeer N, Parmar N, et al. Attention is all you need. Proceedings of the 31st International Conference on Neural Information Processing Systems. Long Beach, CA, USA. 2017. 6000-6010.

[16] Zhou P, Shi W, Tian J, et al. Attention-based bidirectional long short-term memory networks for relation classification. Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics. Berlin, Germany. 2016.

[17] 李卫疆, 李涛, 漆芳. 基于多特征自注意力BLSTM的中文实体关系抽取. 中文信息学报, 2019, 33(10): 47-56, 72. [doi: 10.3969/j.issn.1003-0077.2019.10.006

Get Citation

葛艳,郑利杰,杜军威,陈卓.基于BLSTM-Attention神经网络模型的化工事故分类.计算机系统应用,2020,29(10):205-210

Copy

Article Metrics

Abstract:
PDF:
HTML:
Cited by:

History

Received:February 28,2020
Revised:March 17,2020
Adopted:
Online: September 30,2020
Published: October 15,2020

Article QR Code

You are the first992285Visitors
Copyright: Institute of Software, Chinese Academy of Sciences Beijing ICP No. 05046678-3
Address：4# South Fourth Street, Zhongguancun,Haidian, Beijing,Postal Code：100190
Phone：010-62661041 Fax： Email：csa (a) iscas.ac.cn
Technical Support：Beijing Qinyun Technology Development Co., Ltd.

Beijing Public Network Security No. 11040202500063