Tensor Graph Convolutional Networks for Text Classification
This addresses text classification, a key task in natural language processing, by integrating multiple graph types, but it appears incremental as it builds on existing graph-based neural network methods.
The paper tackles text classification by proposing TensorGCN, a framework that constructs a text graph tensor to capture semantic, syntactic, and sequential information, and uses intra- and inter-graph propagation for learning. Results on benchmark datasets show its effectiveness in harmonizing heterogeneous graph information.
Compared to sequential learning models, graph-based neural networks exhibit some excellent properties, such as ability capturing global information. In this paper, we investigate graph-based neural networks for text classification problem. A new framework TensorGCN (tensor graph convolutional networks), is presented for this task. A text graph tensor is firstly constructed to describe semantic, syntactic, and sequential contextual information. Then, two kinds of propagation learning perform on the text graph tensor. The first is intra-graph propagation used for aggregating information from neighborhood nodes in a single graph. The second is inter-graph propagation used for harmonizing heterogeneous information between graphs. Extensive experiments are conducted on benchmark datasets, and the results illustrate the effectiveness of our proposed framework. Our proposed TensorGCN presents an effective way to harmonize and integrate heterogeneous information from different kinds of graphs.