Understanding Graph Convolutional Networks for Text Classification
This work addresses a gap in applying GCNs to text classification for researchers, but it is incremental as it focuses on analysis rather than introducing new methods.
The paper tackles the problem of understanding how graph construction techniques and GCN learning mechanisms affect text classification performance, providing insights into the importance of node/edge embeddings and training methods across various benchmarks.
Graph Convolutional Networks (GCN) have been effective at tasks that have rich relational structure and can preserve global structure information of a dataset in graph embeddings. Recently, many researchers focused on examining whether GCNs could handle different Natural Language Processing tasks, especially text classification. While applying GCNs to text classification is well-studied, its graph construction techniques, such as node/edge selection and their feature representation, and the optimal GCN learning mechanism in text classification is rather neglected. In this paper, we conduct a comprehensive analysis of the role of node and edge embeddings in a graph and its GCN learning techniques in text classification. Our analysis is the first of its kind and provides useful insights into the importance of each graph node/edge construction mechanism when applied at the GCN training/testing in different text classification benchmarks, as well as under its semi-supervised environment.