A Word-Concept Heterogeneous Graph Convolutional Network for Short Text Classification

• Published in: Neural processing letters Vol. 55; no. 1; pp. 735 - 750
• Main Authors: Yang, Shigang, Liu, Yongguo, Zhang, Yun, Zhu, Jiajing
• Format: Journal Article
• Language: English
• Published: New York Springer US 01.02.2023; Springer Nature B.V
• Subjects: Artificial Intelligence; Artificial neural networks; Classification; Complex Systems; Computational Intelligence; Computer Science; Convolution; Deep learning; Knowledge; Natural language processing; Neural networks; Noise; Representations; Semantics; Sparsity; Support vector machines; Text categorization; Texts; Words (language); Concepts; Short text classification; Graph convolution network; Words
• ISSN: 1370-4621; 1573-773X
• DOI: 10.1007/s11063-022-10906-6

Text classification is an important task in natural language processing. However, most of the existing models focus on long texts, and their performance in short texts is not satisfied due to the problem of data sparsity. To solve this problem, recent studies have introduced the concepts of words to enrich the representation of short texts. However, these methods ignore the interactive information between words and concepts and lead introduced concepts to be noises unsuitable for semantic understanding. In this paper, we propose a new model called word-concept heterogeneous graph convolution network (WC-HGCN) to introduce interactive information between words and concepts for short text classification. WC-HGCN develops words and relevant concepts and adopts graph convolution networks to learn the representation with interactive information. Furthermore, we design an innovative learning strategy, which can make full use of the introduced concept information. Experimental results on seven real short text datasets show that our model outperforms latest baseline methods.