A semantic hierarchical graph neural network for text classification

TL;DR

This paper introduces a hierarchical graph neural network that captures multi-level semantic information in text for improved classification, outperforming or matching existing methods on benchmark datasets.

Contribution

The paper presents a novel hierarchical GNN that extracts semantic features at word, sentence, and document levels for enhanced text classification.

Findings

Achieves better or comparable results on benchmark datasets

Effectively captures multi-level semantic information

Demonstrates the advantage of hierarchical structure in GNNs

Abstract

The key to the text classification task is language representation and important information extraction, and there are many related studies. In recent years, the research on graph neural network (GNN) in text classification has gradually emerged and shown its advantages, but the existing models mainly focus on directly inputting words as graph nodes into the GNN models ignoring the different levels of semantic structure information in the samples. To address the issue, we propose a new hierarchical graph neural network (HieGNN) which extracts corresponding information from word-level, sentence-level and document-level respectively. Experimental results on several benchmark datasets achieve better or similar results compared to several baseline methods, which demonstrate that our model is able to obtain more useful information for classification from samples.