LGSA: Label Geometry Structuring and Aligning for Hierarchical Text Classification

ACL ARR 2026 January Submission1840 Authors

Keywords: Hierarchical text classification, Long-tailed distribution, Spatial geometry, General orthogonal frame

Abstract: Existing hierarchical text classification (HTC) methods typically use prompt tuning or contrastive learning to inject the label hierarchy into a model as prior knowledge to implicitly learn label embeddings for classification. However, such implicit learning fails to accurately reflect label geometry (i.e., feature spatial distribution of label embeddings), as it does not model hierarchy-aware geometric relations among labels. To address this issue, we propose a novel two-stage label geometry structuring and aligning framework, termed LGSA, which transforms the label hierarchy from an implicit prior into an explicit embedding. First, we propose a hierarchical geometric structuring (HGS) module that leverages a general orthogonal frame (GOF) to reconstruct an explicit label geometry conforming to the label hierarchy. The label geometry is then treated as a label prototype to guide model training. To facilitate the guidance, we thereby propose a hierarchical geometric aligning (HGA) module as a regularization term to align label geometry learned by the model with the explicit label prototype. Experiments on three real-world HTC datasets confirm that LGSA consistently outperforms existing state-of-the-art methods. The code and models are available at https://anonymous.4open.science/r/LGSA-1E0C.

Paper Type: Long

Research Area: Machine Learning for NLP

Research Area Keywords: representation learning, word embeddings, structured prediction, optimization methods

Contribution Types: Model analysis & interpretability, NLP engineering experiment

Languages Studied: English

Submission Number: 1840