SCHK-HTC: Sibling Contrastive Learning with Hierarchical Knowledge-Aware Prompt Tuning for Hierarchical Text Classification

TL;DR

SCHK-HTC introduces a hierarchical knowledge-aware prompt tuning and sibling contrastive learning framework to improve few-shot hierarchical text classification by better distinguishing semantically similar sibling classes.

Contribution

It proposes a novel framework with hierarchical knowledge extraction and sibling contrastive learning to enhance class separability in few-shot HTC tasks.

Findings

Achieves superior performance on three benchmark datasets.

Outperforms existing state-of-the-art methods in most cases.

Effectively encodes discriminative features at each hierarchy level.

Abstract

Few-shot Hierarchical Text Classification (few-shot HTC) is a challenging task that involves mapping texts to a predefined tree-structured label hierarchy under data-scarce conditions. While current approaches utilize structural constraints from the label hierarchy to maintain parent-child prediction consistency, they face a critical bottleneck, the difficulty in distinguishing semantically similar sibling classes due to insufficient domain knowledge. We introduce an innovative method named Sibling Contrastive Learning with Hierarchical Knowledge-aware Prompt Tuning for few-shot HTC tasks (SCHK-HTC). Our work enhances the model's perception of subtle differences between sibling classes at deeper levels, rather than just enforcing hierarchical rules. Specifically, we propose a novel framework featuring two core components: a hierarchical knowledge extraction module and a sibling contrastive learning mechanism. This design guides model to encode discriminative features at each hierarchy level, thus improving the separability of confusable classes. Our approach achieves superior performance across three benchmark datasets, surpassing existing state-of-the-art methods in most cases. Our code is available at https://github.com/happywinder/SCHK-HTC.