Incorporating Hierarchy into Text Encoder: a Contrastive Learning Approach for Hierarchical Text Classification
This addresses hierarchical text classification, a challenging multi-label task, with a novel approach that integrates hierarchy into text encoding, though it appears incremental as it builds on contrastive learning methods.
The paper tackles hierarchical text classification by proposing Hierarchy-guided Contrastive Learning (HGCLR) to embed label hierarchy directly into a text encoder, eliminating the need for separate hierarchy modeling. Experiments on three benchmark datasets show its effectiveness, though no specific numerical results are provided in the abstract.
Hierarchical text classification is a challenging subtask of multi-label classification due to its complex label hierarchy. Existing methods encode text and label hierarchy separately and mix their representations for classification, where the hierarchy remains unchanged for all input text. Instead of modeling them separately, in this work, we propose Hierarchy-guided Contrastive Learning (HGCLR) to directly embed the hierarchy into a text encoder. During training, HGCLR constructs positive samples for input text under the guidance of the label hierarchy. By pulling together the input text and its positive sample, the text encoder can learn to generate the hierarchy-aware text representation independently. Therefore, after training, the HGCLR enhanced text encoder can dispense with the redundant hierarchy. Extensive experiments on three benchmark datasets verify the effectiveness of HGCLR.