基于弱化图卷积网络的文本分类

doi:10.11896/jsjkx.220700039

计算机科学 ›› 2023, Vol. 50 ›› Issue (6A): 220700039-5.doi: 10.11896/jsjkx.220700039

基于弱化图卷积网络的文本分类

黄玉娇¹, 陈铭凯¹, 郑媛¹, 范兴刚¹, 肖杰², 龙海霞²

1 浙江工业大学之江学院浙江绍兴 312030;
2 浙江工业大学计算机科学与技术学院杭州 310000

出版日期:2023-06-10 发布日期:2023-06-12
通讯作者: 黄玉娇(huangyuajiao@zjut.edu.cn)
基金资助:
国家自然科学基金(61972354,62106225);浙江省自然科学基金(LY20F020024,LZ22F020011)

Text Classification Based on Weakened Graph Convolutional Networks

HUANG Yujiao¹, CHEN Mingkai¹, ZHENG Yuan¹, FAN Xinggang¹, XIAO Jie², LONG Haixia²

1 Zhijiang College of Zhejiang University of Technology,Shaoxing,Zhejiang 312030,China;
2 College of Computer Science and Technology,Zhejiang University of Technology,Hangzhou 310000,China

Online:2023-06-10 Published:2023-06-12
About author:HUANG Yujiao,born in 1985,Ph.D,associate professor.Her main research interests include deep learning,text data analysis and dynamic characteristics of neural networks.
Supported by:
National Natural Science Foundation of China(61972354,62106225) and Natural Science Foundation of Zhejiang Pvovince,China(LY20F020024,LZ22F020011).

摘要/Abstract

摘要： 文本分类是自然语言处理领域中的经典问题。传统的文本分类模型存在需要人工提取特征,分类准确率不高,难以处理非欧氏空间数据等问题。为了解决上述问题,进一步提高文本分类的准确率,提出了W-GCN模型。该模型在Text-GCN模型的基础上加以改进,建立了全新的弱化结构模型,用以替换Text-GCN模型中对神经元的Dropout操作,并通过弱化权重,精确控制弱化力度大小,在一定程度保留Dropout防止过拟合功能的基础上,避免了由直接丢弃神经元造成的特征丢失问题,因此提高了模型分类的准确率。与Text-GCN模型相比,基于弱化图卷积网络建立的W-GCN模型,在R8数据集上准确率提高了0.38%,在R52数据集上准确率提高了0.62%。实验结果证明了模型改进和弱化结构的有效性。

关键词: 图卷积网络, 文本分类, 文本图构建方法, 弱化结构, Dropout

Abstract: Text classification is a classic problem in the field of natural language processing.The traditional text classification model needs to extract features manually,the classification accuracy is not high,and it is difficult to deal with non-European spatial data.In order to solve the above problems and further improve the accuracy of text classification,the W-GCN model is proposed.This model is improved on the basis of the Text-GCN model,and a new weakened structure model is established to replace the text-GCN model.The dropout operation of neurons,and by weakening the weight,accurately control the weakening strength,and on the basis of retaining the dropout to a certain extent to prevent overfitting,it avoids the loss of features caused by directly discarding neurons,thus improving the accuracy of model classification..Compared with the Text-GCN model,the W-GCN model based on the weakened graph convolutional network improves the accuracy by 0.38% on the R8 dataset and 0.62% on the R52 dataset.The experimental results prove that the model Improve and weaken the effectiveness of the structure.

Key words: Graph convolutional neural networks, Text classification, Construction method of text map, Weakened structure, Droupout

中图分类号:

TP391

黄玉娇, 陈铭凯, 郑媛, 范兴刚, 肖杰, 龙海霞. 基于弱化图卷积网络的文本分类[J]. 计算机科学, 2023, 50(6A): 220700039-5. https://doi.org/10.11896/jsjkx.220700039

HUANG Yujiao, CHEN Mingkai, ZHENG Yuan, FAN Xinggang, XIAO Jie, LONG Haixia. Text Classification Based on Weakened Graph Convolutional Networks[J]. Computer Science, 2023, 50(6A): 220700039-5. https://doi.org/10.11896/jsjkx.220700039

参考文献

[1]CARRERAS X,MARQUEZ L.Boosting trees for anti-spamemail filtering[C]//Proceedings of European Conference Recent Advances in NLP.2001:58-64.
[2]AGGARWAL C C,ZHAI C X.A survey of text classification algorithms[M].US:Mining Text Data,Springer,2012.
[3]MCCALLUM A,NIGAM K.A comparison of event models for naive bayes text classificatin[C]//AAAI-98 Workshop on Learning for Text Categorization.1998:41-48.
[4]JOACHIMS T.Text categorization with support vector ma-chines:Learning with many relevant features[C]//Proceedings of the 10th European Conference on Machine Learning.1998:137-142.
[5]WANG X,CHEN R,JIA Y,et al.Short text classification using wikipedia concept based document representation[C]//International Conference on Information Technology and Applications.2013:471-474.
[6]LECUN Y,BOTTOU L.Gradient-based learning applied to docu-ment recognition[C]//Proceedings of the IEEE.1998:2278-2324.
[7]ZHOU J,CUI G,ZHANG Z,et al.Graph neural networks:A review of methods and applications[J].arXiv:1812.08434,2018.
[8]WU Z,PAN S,CHEN F,et al.A Comprehensive Survey onGraph Neural Networks[J].IEEE Transactions on Neural Networks and Learning Systems,2021,32(1):4-24.
[9]ZHANG Z,CUI P,ZHU W. Deep Learning on Graphs:A Survey[J].IEEE Transactions on Knowledge and Data Engineering,2022,34(1):249-270.
[10]ZHOU J,CUI G,HU S,et al.Graph neural networks:A review of methods and applications[J].AI Open,2020,1:57-81.
[11]DEFFERRARD M,BRESSON X,VANDERGHEYNST P,et al.Convolutional neural networks on graphs with fastlocali-zed spectral filtering[C]//Neural Information Processing Systems.2016:3844-3852.
[12]YAO L,MAO C,LUO Y.Graph Convolutional Networks for Text Classification[C]//Proceedings of the AAAI Conference on Artificial Intelligence.2019:7370-7377.
[13]HINTON G E,SRIVASTAVA N,KRIZHEVSKY A,et al.Improving neural networks by preventing co-adaptation of feature detectors[J].Computer Science,2012,3(4):212-223.
[14]SRIVASTAVA N,HINTON G,KRIZHEVSKY A,et al.Dropout:A Simple Way to Prevent Neural Networks from Overfitting[J].Journal of Machine Learning Research,2014,15(1):1929-1958.
[15]BLEID M,NG A Y,JORDAN M I.Latent dirichlet allocation[J].Journal of Machine Learning Research,2003,3(1):933-1022.
[16]LAI S,XU L,LIU K,et al.Recurrent convolutional neural networks for text classification[C]//Proceedings of the AAAI Conference on Artificial Intelligence.2015:2267-2273.
[17]CHEN B.Graph convolution neural network algorithm for text classification[D].Guilin:Guangxi Normal University,2021.
[18]WANG T,ZHU X F,TANG G.Text classification based on graph convolution neural network with knowledge enhancement[J].Journal of Zhejiang University (Engineering Edition),2022,56(2):322-328.

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed

基于弱化图卷积网络的文本分类

Text Classification Based on Weakened Graph Convolutional Networks

PDF (PC)

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 0

Metrics

本文评价

推荐阅读 0