VGCN-BERT: Augmenting BERT with Graph Embedding for Text Classification
This is an incremental improvement for text classification tasks, addressing a specific limitation in existing models.
The paper tackles the problem of text classification by augmenting BERT with a Vocabulary Graph Convolutional Network (VGCN) to capture both local contextual and global vocabulary information, resulting in improved performance over BERT and GCN alone on several datasets.
Much progress has been made recently on text classification with methods based on neural networks. In particular, models using attention mechanism such as BERT have shown to have the capability of capturing the contextual information within a sentence or document. However, their ability of capturing the global information about the vocabulary of a language is more limited. This latter is the strength of Graph Convolutional Networks (GCN). In this paper, we propose VGCN-BERT model which combines the capability of BERT with a Vocabulary Graph Convolutional Network (VGCN). Local information and global information interact through different layers of BERT, allowing them to influence mutually and to build together a final representation for classification. In our experiments on several text classification datasets, our approach outperforms BERT and GCN alone, and achieve higher effectiveness than that reported in previous studies.