HILL: Hierarchy-aware Information Lossless Contrastive Learning for Hierarchical Text Classification

arXiv:2403.17307v1 Announce Type: new
Abstract: Existing self-supervised methods in natural language processing (NLP), especially hierarchical text classification (HTC), mainly focus on self-supervised contrastive learning, extremely relying on human-designed augmentation rules to generate contrastive samples, which can potentially corrupt or distort the original information. In this paper, we tend to investigate the feasibility of a contrastive learning scheme in which the semantic and syntactic information inherent in the input sample is adequately reserved in the contrastive samples and fused during the …

abstract arxiv augmentation classification cs.cl cs.it focus generate hierarchical hill human information language language processing math.it natural natural language natural language processing nlp paper processing rules samples text text classification type