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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Semi-supervised text classification (SSTC) has gained increasing attentiondue to its ability to leverage unlabeled data. However, existing approachesbased on pseudo-labeling suffer from the issues of pseudo-label bias and erroraccumulation. In this paper, we propose JointMatch, a holistic approach forSSTC that addresses these challenges by unifying ideas from recentsemi-supervised learning and the task of learning with noise. JointMatchadaptively adjusts classwise thresholds based on the learning status ofdifferent classes to mitigate model bias towards current easy classes.Additionally, JointMatch alleviates error accumulation by utilizing twodifferently initialized networks to teach each other in a cross-labelingmanner. To maintain divergence between the two networks for mutual learning, weintroduce a strategy that weighs more disagreement data while also allowing theutilization of high-quality agreement data for training. Experimental resultson benchmark datasets demonstrate the superior performance of JointMatch,achieving a significant 5.13% improvement on average. Notably, JointMatchdelivers impressive results even in the extremely-scarce-label setting,obtaining 86% accuracy on AG News with only 5 labels per class. We make ourcode available at https://github.com/HenryPengZou/JointMatch.

JointMatch: A Unified Approach for Diverse and Collaborative Pseudo-Labeling to Semi-Supervised Text Classification