International Conference on Computer and Knowledge Engineering

Home / 14th International Conference on Computer and Knowledge Engineering

Supervised Contrastive Learning for Short Text Classification in Natural Language Processing

Authors :

Mitra Esmaeili¹ Hamed Vahdat nejad²

1- Perlab, Faculty of Electrical and Computer Engineering, University of Birjand, Birjand, Iran 2- Perlab, Faculty of Electrical and Computer Engineering, University of Birjand, Birjand, Iran

Keywords :

Supervised Contrastive Learning،Text Classification،Natural Language Processing،Semantic Understanding

Abstract :

In recent years, the swift progress in information retrieval technologies has positioned text classification as a key area of research. Classifying short texts represents a major challenge within the domain of natural language processing. Given the growing prevalence of social media during critical events like hurricanes, accurately categorizing these texts is essential for facilitating evaluation and relief operations. Tweets, characterized by their conciseness and informal tone, present unique challenges for effective classification. Supervised contrastive learning has recently gained prominence as a powerful machine learning method, offering significant improvements over traditional approaches, particularly in the NLP field. This paper introduces a supervised contrastive learning strategy designed to enhance the precision of short text classification while maintaining the model’s generalization capability. Our approach consistently surpasses existing state-of-the-art techniques, delivering better accuracy and stability across a range of NLP tasks.