English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Hierarchical multi-label text classification (HMTC) aims at utilizing a labelhierarchy in multi-label classification. Recent approaches to HMTC deal withthe problem of imposing an over-constrained premise on the output space byusing contrastive learning on generated samples in a semi-supervised manner tobring text and label embeddings closer. However, the generation of samplestends to introduce noise as it ignores the correlation between similar samplesin the same batch. One solution to this issue is supervised contrastivelearning, but it remains an underexplored topic in HMTC due to its complexstructured labels. To overcome this challenge, we propose $\textbf{HJCL}$, a$\textbf{H}$ierarchy-aware $\textbf{J}$oint Supervised $\textbf{C}$ontrastive$\textbf{L}$earning method that bridges the gap between supervised contrastivelearning and HMTC. Specifically, we employ both instance-wise and label-wisecontrastive learning techniques and carefully construct batches to fulfill thecontrastive learning objective. Extensive experiments on four multi-path HMTCdatasets demonstrate that HJCL achieves promising results and the effectivenessof Contrastive Learning on HMTC.

Instances and Labels: Hierarchy-aware Joint Supervised Contrastive Learning for Hierarchical Multi-Label Text Classification