• 综合
  • 标题
  • 关键词
  • 摘要
  • 学者
  • 期刊-刊名
  • 期刊-ISSN
  • 会议名称
搜索

作者:

Xue, Bingxin (Xue, Bingxin.) | Zhu, Cui (Zhu, Cui.) | Wang, Xuan (Wang, Xuan.) | Zhu, Wenjun (Zhu, Wenjun.)

收录:

Scopus SCIE

摘要:

Graph Convolutional Neural Network (GCN) is widely used in text classification tasks. Furthermore, it has been effectively used to accomplish tasks that are thought to have a rich relational structure. However, due to the sparse adjacency matrix constructed by GCN, GCN cannot make full use of context-dependent information in text classification, and it is not good at capturing local information. The Bidirectional Encoder Representation from Transformers (BERT) has the ability to capture contextual information in sentences or documents, but it is limited in capturing global (the corpus) information about vocabulary in a language, which is the advantage of GCN. Therefore, this paper proposes an improved model to solve the above problems. The original GCN uses word co-occurrence relationships to build text graphs. Word connections are not abundant enough and cannot capture context dependencies well, so we introduce a semantic dictionary and dependencies. While the model enhances the ability to capture contextual dependencies, it lacks the ability to capture sequences. Therefore, we introduced BERT and Bi-directional Long Short-Term Memory (BiLSTM) Network to perform deeper learning on the features of text, thereby improving the classification effect of the model. The experimental results show that our model is more effective than previous research reports on four text classification datasets.

关键词:

Bi-directional Long Short-Term Memory ResNet graph convolutional network dependencies text classification

作者机构:

  • [ 1 ] [Xue, Bingxin]Beijing Univ Technol, Fac Informat Technol, Beijing 100020, Peoples R China
  • [ 2 ] [Zhu, Cui]Beijing Univ Technol, Fac Informat Technol, Beijing 100020, Peoples R China
  • [ 3 ] [Wang, Xuan]Beijing Univ Technol, Fac Informat Technol, Beijing 100020, Peoples R China
  • [ 4 ] [Zhu, Wenjun]Beijing Univ Technol, Fac Informat Technol, Beijing 100020, Peoples R China

通讯作者信息:

电子邮件地址:

查看成果更多字段

相关关键词:

来源 :

APPLIED SCIENCES-BASEL

年份: 2022

期: 16

卷: 12

2 . 7

JCR@2022

2 . 7 0 0

JCR@2022

ESI学科: ENGINEERING;

ESI高被引阀值:49

JCR分区:2

中科院分区:3

被引次数:

WoS核心集被引频次: 6

SCOPUS被引频次:

ESI高被引论文在榜: 0 展开所有

万方被引频次:

中文被引频次:

近30日浏览量: 0

归属院系:

在线人数/总访问数:556/4955602
地址:北京工业大学图书馆(北京市朝阳区平乐园100号 邮编:100124) 联系我们:010-67392185
版权所有:北京工业大学图书馆 站点建设与维护:北京爱琴海乐之技术有限公司