Pith. sign in

REVIEW 3 cited by

Incorporating Hierarchy into Text Encoder: a Contrastive Learning Approach for Hierarchical Text Classification

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2203.03825 v2 pith:WTKMZB33 submitted 2022-03-08 cs.CL

Zihan Wang , Peiyi Wang , Lianzhe Huang , Xin Sun , Houfeng Wang This is my paper · ORCID
classification cs.CL
keywords texthierarchyclassificationencoderhgclrinputlabelcontrastive
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original 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.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 3 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Cross-Layer Misalignment Detection in Agent Skills: A Progressive Loading-Aware Contrastive Learning Approach

    cs.AI 2026-07 conditional novelty 6.0 of 10

    PL-HCL detects cross-layer misalignment in Agent Skills by learning consistency among metadata, instructions, and resources, lifting Macro-F1 to 0.87–0.89 on a human-verified challenge set.

  2. Learning Taxonomic Trees with Hierarchical Representation Regularization for Large Multimodal Models

    cs.CV 2026-07 conditional novelty 6.0 of 10

    HiR² extracts coarse-to-fine visual features from LMM layers and regularizes them with Lorentz entailment cones and unit-sphere dispersive loss, improving hierarchical consistency across models and fine-tuning methods.

  3. Enhancing Text-Based Hierarchical Multilabel Classification for Mobile Applications via Contrastive Learning

    cs.LG 2025-07 conditional novelty 5.0 of 10

    HMCL, a level-wise negative-sampling contrastive pretraining scheme, improves HMCN's hierarchical multilabel classification for mobile apps and achieved a reported 10.70% KS improvement in a downstream credit-risk task.

Pith tools