Every Document Owns Its Structure: Inductive Text Classification via Graph Neural Networks
This work addresses a specific bottleneck in NLP by improving inductive text classification for researchers and practitioners, though it is incremental as it builds on existing GNN approaches.
The authors tackled the problem of text classification by proposing TextING, a Graph Neural Network method that builds individual graphs per document to capture contextual word relationships and enable inductive learning for new words, achieving state-of-the-art performance on four benchmark datasets.
Text classification is fundamental in natural language processing (NLP), and Graph Neural Networks (GNN) are recently applied in this task. However, the existing graph-based works can neither capture the contextual word relationships within each document nor fulfil the inductive learning of new words. In this work, to overcome such problems, we propose TextING for inductive text classification via GNN. We first build individual graphs for each document and then use GNN to learn the fine-grained word representations based on their local structures, which can also effectively produce embeddings for unseen words in the new document. Finally, the word nodes are aggregated as the document embedding. Extensive experiments on four benchmark datasets show that our method outperforms state-of-the-art text classification methods.