融合LDA的门控图卷积网络文本分类研究  

Incorporating LDA into gated graph convolutional networks for the study of text classification

作　　者：高维奇 黄浩[1,2,3] 胡英 吾守尔·斯拉木 GAO Wei-qi;HUANG Hao;HU Ying;WUSHOUR Silamu(School of Information Science and Engineering,Xinjiang University,Urumqi 830046,China;Multi-language Information Technology Laboratory of Xinjiang,Urumqi 830046,China;Multi-language Information Technology Research Center of Xinjiang,Urumqi 830046,China)

机构地区：[1]新疆大学信息科学与工程学院,新疆乌鲁木齐830046 [2]新疆多语种信息技术实验室,新疆乌鲁木齐830046 [3]新疆多语种信息技术研究中心,新疆乌鲁木齐830046

出　　处：《东北师大学报（自然科学版）》2021年第4期68-76,共9页Journal of Northeast Normal University(Natural Science Edition)

基　　金：国家重点研发计划项目(2017YFB1402101);国家自然科学基金资助项目(61663044,61761041);新疆重点科技项目(2016A03007-1);新疆高等教育创新项目(XJEDU2017T002).

摘　　要：在现有文本图基础上引入隐狄利克雷分布,将文档-主题和主题-词信息融入文本图以丰富文本图中节点间关系,之后将该文本图送入一个基于图卷积网络门控机制模型.在多个数据集上进行验证.结果表明,所提出的模型优于现有图卷积网络文本分类模型.At present,graph convolutional network based text classification model uses word co-occurrence and word frequency-inverse document frequency(TF-IDF)information for graph construction.In this paper,we introduce the Latent Dirichlet Allocation(LDA)to construct text graph based on the existing text graph,and integrate the document-topic and topic-word information into the text graph,thereby enriching the relationship between the nodes in the text graph,and then feed the text graph into a gating mechanism model based on graph convolutional network(G-GCN).Verification on multiple datasets show that the model proposed in this paper is superior to existing text classification models based on graph convolutional networks.

关 键 词：文本分类 图卷积网络 隐狄利克雷分布 门控机制 文本图 

分 类 号：TP391.1[自动化与计算机技术—计算机应用技术]