Hierarchical Heterogeneous Graph Representation Learning for Short Text Classification
This addresses the problem of short text classification for NLP practitioners, offering improved performance in data-scarce scenarios, though it is incremental as it builds on existing GNN approaches.
The paper tackles short text classification by proposing SHINE, a graph neural network method that models datasets as hierarchical heterogeneous graphs to capture semantic and syntactic information, and it outperforms state-of-the-art methods, particularly with limited labeled data.
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.