AI Paper Atlas

Research map / Label-efficient and robust learning / Semi-supervised learning

Contrast-Enhanced Semi-supervised Text Classification with Few Labels

Austin Cheng-Yun Tsai, Sheng-Ya Lin, Li-Chen Fu

AAAI 2022 · Label-efficient and robust learning › Semi-supervised learning · approach: Holistic semi-supervised pipelines · 20 citations (OpenAlex)

Read the paper

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Add certainty-driven sample selection (ablation)CEST · five benchmark datasetsaverage test accuracy (%): 87.89 -> 91.57Improved
Add the noise-robust PHCE loss (ablation)CEST · five benchmark datasetsaverage test accuracy (%): 91.04 -> 91.57Improved
Add reliable sub-graph construction (ablation)CEST · five benchmark datasetsaverage test accuracy (%): 90.46 -> 91.57Improved
Add smoothness regularization (ablation)CEST · five benchmark datasetsaverage test accuracy (%): 89.97 -> 91.57Improved
Use CEST instead of USTBERT semi-supervised text classification · five benchmark datasetsaverage test accuracy (%): 89.46 (+5.85%) -> 91.57 (+7.96%)Improved
Use CEST instead of UDABERT semi-supervised text classification · five benchmark datasetsaverage test accuracy (%): 89.06 (+5.45%) -> 91.57 (+7.96%)Improved
Use CEST instead of BERT fine-tuning without unlabeled dataBERT · five benchmark datasetsaverage test accuracy (%): 83.61 (+0.00%) -> 91.57 (+7.96%)Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy