.png){kind=icon}
.png){kind=icon}
Return
Text classification based on PEGCN: Graph convolution classification using location information and edge features
.png){kind=icon}
PRE
AI
DOI：10.1111/exsy.13511.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
The purpose of text classification is to label the text with known labels. In recent years, the method based on graph neural network (GNN) has achieved good results. However, the existing methods based on GNN only regard the text as the set of co-occurring words, without considering the position information of each word in the statement. At the same time, the method mainly extracts the node features in the graph, and the edge features between the nodes are not used enough. To solve these problems, a new text classification method, graph convolutional network using positions and edges, is proposed. In the word embedding section, a positional encoding input representation is employed to enable the neural network to learn the relative positional information among words. Meanwhile, the dimension of the adjacency matrix is increased to extract the multi-dimensional edge features. Through experiments on multiple text classification datasets, the proposed method is shown to be superior to the traditional text classification method, and has achieved a maximum improvement of more than 4%.
Keywords:
deep learning
graph convolutional networks
natural language processing
text classification
Journal
IF:
2.3
Papers:
2.5K
Citations:
3.8K
Organization
No organization information available