BertGCN - Transductive Text Classification by Combining GNN and BERT.

ACL/IJCNLP(2021)

引用 178|浏览713
暂无评分
摘要
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.
更多
查看译文
关键词
transductive text classification,bertgcn
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络