Every Document Owns Its Structure: Inductive Text Classification via Graph Neural Networks

TL;DR

This paper introduces TextING, a graph neural network approach that constructs individual document graphs to improve inductive text classification by capturing local word relationships and handling unseen words effectively.

Contribution

The paper presents a novel GNN-based method that builds separate graphs per document, enabling better inductive learning and contextual word relationship modeling.

Findings

Outperforms state-of-the-art methods on four benchmark datasets.

Effectively produces embeddings for unseen words.

Captures fine-grained local word relationships within documents.

Abstract

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.