BertGCN: Transductive Text Classification by Combining GCN and BERT

TL;DR

BertGCN is a novel model that combines BERT's large-scale pretraining with graph convolutional networks for transductive text classification, effectively leveraging both raw data and test data during training.

Contribution

It introduces a method that integrates BERT and GCN in a transductive learning framework for improved text classification performance.

Findings

Achieves state-of-the-art results on multiple datasets.

Effectively propagates label information through graph convolution.

Combines pretraining and transductive learning advantages.

Abstract

In this work, we propose BertGCN, a model that combines large scale pretraining and transductive learning for text classification. BertGCN constructs a heterogeneous graph over the dataset and represents documents as nodes using BERT representations. By jointly training the BERT and GCN modules within BertGCN, the proposed model is able to leverage the advantages of both worlds: large-scale pretraining which takes the advantage of the massive amount of raw data and transductive learning which jointly learns representations for both training data and unlabeled test data by propagating label influence through graph convolution. Experiments show that BertGCN achieves SOTA performances on a wide range of text classification datasets. Code is available at https://github.com/ZeroRin/BertGCN.