Text Classification Method Based on Bidirectional Attention and Gated Graph Convolutional Networks

• Published in: Ji suan ji ke xue Vol. 50; no. 1; pp. 221 - 228
• Main Authors: Zheng, Cheng, Mei, Liang, Zhao, Yiyan, Zhang, Suhang
• Format: Journal Article
• Language: Chinese
• Published: Chongqing Guojia Kexue Jishu Bu 01.01.2023; Editorial office of Computer Science
• Subjects: Artificial neural networks; Classification; Documents; Embedding; Graphical representations; Networks; Nodes; Text categorization; text classification|graph convolutional networks|attention mechanism|text representation|deep learning|natural language processing
• ISSN: 1002-137X
• DOI: 10.11896/jsjkx.211100095

Existing text classification models based on graph convolutional networks usually simply fuse the neighborhood information of different orders through the adjacency matrix to update the representation of node in graph, resulting in insufficientrepresentation of the word sense information of the nodes.In addition, the model based on conventional attention mechanism only provides a positive weighted representation of the word embedding, ignoring the impact of words that produce negative effects on the final classification.To overcome the above problems, a model based on bidirectional attention mechanism and gated graph convolutional networks is proposed in the paper.Firstly, the model uses the gated graph convolutional networks to selectively fuse the multi-order neighborhood information of nodes in the graph, retaining the information of previous orders, to enrich the feature representation of nodes in graph.Secondly, the model learns the influence of different words on text classification results by the bidir