Hierarchical Heterogeneous Graph Representation Learning for Short Text Classification

TL;DR

SHINE is a novel GNN-based method that models short texts as hierarchical heterogeneous graphs, effectively capturing semantic and syntactic information to improve classification, especially with limited labeled data.

Contribution

The paper introduces SHINE, a hierarchical heterogeneous graph neural network that enhances short text classification by modeling semantic, syntactic, and similarity-based relationships.

Findings

SHINE outperforms existing methods on benchmark datasets.

SHINE is particularly effective with fewer labeled samples.

The hierarchical graph modeling improves semantic and syntactic feature capture.

Abstract

Short text classification is a fundamental task in natural language processing. It is hard due to the lack of context information and labeled data in practice. In this paper, we propose a new method called SHINE, which is based on graph neural network (GNN), for short text classification. First, we model the short text dataset as a hierarchical heterogeneous graph consisting of word-level component graphs which introduce more semantic and syntactic information. Then, we dynamically learn a short document graph that facilitates effective label propagation among similar short texts. Thus, compared with existing GNN-based methods, SHINE can better exploit interactions between nodes of the same types and capture similarities between short texts. Extensive experiments on various benchmark short text datasets show that SHINE consistently outperforms state-of-the-art methods, especially with fewer labels.