Text classification based on graph convolutional network with attention

Abstract

The paper proposes a text classification method based on the graph convolutional network, the traditional text classification problem can be transformed into the node classification problem in the graph, and then proposes a attention structure to increase the weight of certain words and phrases. This paper verifies that the above structure has a positive effect on text classification accuracy. In particular, the structure can handle irregular data, such as citation network. We obtain very competitive results on 5 commonly used text classification datasets and achieve state-of-the-art results on 4 datasets, which include one dataset of citation network. Experiments show that combination of both structures can significantly reduce the classification error.