Improved Graph Contrastive Learning for Short Text Classification

Authors

  • Yonghao Liu Jilin University
  • Lan Huang College of Computer Science and Technology, Jilin University
  • Fausto Giunchiglia University of Trento
  • Xiaoyue Feng Jilin University
  • Renchu Guan The Key Laboratory for Symbol Computation and Knowledge Engineering of the Ministry of Education College of Computer Science and Technology, Jilin University

DOI:

https://doi.org/10.1609/aaai.v38i17.29835

Keywords:

NLP: Text Classification, ML: Classification and Regression, ML: Multi-class/Multi-label Learning & Extreme Classification, NLP: Sentiment Analysis, Stylistic Analysis, and Argument Mining

Abstract

Text classification occupies an important role in natural language processing and has many applications in real life. Short text classification, as one of its subtopics, has attracted increasing interest from researchers since it is more challenging due to its semantic sparsity and insufficient labeled data. Recent studies attempt to combine graph learning and contrastive learning to alleviate the above problems in short text classification. Despite their fruitful success, there are still several inherent limitations. First, the generation of augmented views may disrupt the semantic structure within the text and introduce negative effects due to noise permutation. Second, they ignore the clustering-friendly features in unlabeled data and fail to further utilize the prior information in few valuable labeled data. To this end, we propose a novel model that utilizes improved Graph contrastIve learning for short text classiFicaTion (GIFT). Specifically, we construct a heterogeneous graph containing several component graphs by mining from an internal corpus and introducing an external knowledge graph. Then, we use singular value decomposition to generate augmented views for graph contrastive learning. Moreover, we employ constrained kmeans on labeled texts to learn clustering-friendly features, which facilitate cluster-oriented contrastive learning and assist in obtaining better category boundaries. Extensive experimental results show that GIFT significantly outperforms previous state-of-the-art methods. Our code can be found in https://github.com/KEAML-JLU/GIFT.

Published

2024-03-24

How to Cite

Liu, Y., Huang, L., Giunchiglia, F., Feng, X., & Guan, R. (2024). Improved Graph Contrastive Learning for Short Text Classification. Proceedings of the AAAI Conference on Artificial Intelligence, 38(17), 18716-18724. https://doi.org/10.1609/aaai.v38i17.29835

Issue

Section

AAAI Technical Track on Natural Language Processing II