ScholarGate
⌘K
Assistant
EN
Machine learningDeep learning / NLP / CV

Weakly Supervised BERT-based Classification

Weakly supervised BERT-based classification adapts BERT to text classification tasks when only noisy, heuristic, or programmatically generated labels are available instead of clean human annotations. It combines weak supervision frameworks — such as labeling functions and data programming — with BERT's pre-trained language representations to achieve robust classification without expensive hand-labeling.

Open in MethodMindSoonVideoSoon

Read the full method

Members only

Sign in with a free account to read this section.

Sign in

Sources

  1. Meng, Y., Zhang, Y., Huang, J., Xiong, C., Ji, H., Zhang, C., & Han, J. (2020). Text Classification Using Label Names Only: A Language Model Self-Training Approach. Proceedings of EMNLP 2020, 9006–9017. link ↗
  2. Ratner, A., Bach, S. H., Ehrenberg, H., Fries, J., Wu, S., & Re, C. (2017). Snorkel: Rapid Training Data Creation with Weak Supervision. Proceedings of the VLDB Endowment, 11(3), 269–282. DOI: 10.14778/3157794.3157797 ↗

Related methods

BERT-based ClassificationDomain-adaptive BERT-based ClassificationFine-Tuned BERT-based ClassificationRoBERTa-based ClassificationSelf-supervised BERT-based classificationSemi-supervised BERT-based Classification

Referenced by

Semi-supervised BERT-based ClassificationWeakly supervised LDA topic modelWeakly Supervised RoBERTa-based ClassificationWeakly supervised sentence embeddingsWeakly supervised transformer

Spotted an issue on this page? Report or suggest a fix →

ScholarGate — Weakly supervised BERT-based classification (Weakly Supervised BERT-based Text Classification). Retrieved 2026-06-04 from https://scholargate.app/en/deep-learning/weakly-supervised-bert-based-classification