Text Level Graph Neural Network for Text Classification
This work addresses practical issues in text classification for researchers and practitioners by enabling online testing and reducing memory usage, though it is incremental as it builds on existing GNN methods.
The paper tackles the problems of fixed corpus-level graph structures and high memory consumption in graph neural networks for text classification by proposing a model that builds graphs per input text with global parameter sharing and smaller windows, resulting in outperforming existing models on several datasets with less memory consumption.
Recently, researches have explored the graph neural network (GNN) techniques on text classification, since GNN does well in handling complex structures and preserving global information. However, previous methods based on GNN are mainly faced with the practical problems of fixed corpus level graph structure which do not support online testing and high memory consumption. To tackle the problems, we propose a new GNN based model that builds graphs for each input text with global parameters sharing instead of a single graph for the whole corpus. This method removes the burden of dependence between an individual text and entire corpus which support online testing, but still preserve global information. Besides, we build graphs by much smaller windows in the text, which not only extract more local features but also significantly reduce the edge numbers as well as memory consumption. Experiments show that our model outperforms existing models on several text classification datasets even with consuming less memory.