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

Semi-supervised RoBERTa-based Classification

Semi-supervised RoBERTa-based classification combines a large pretrained RoBERTa language model with both a small labeled dataset and a larger pool of unlabeled text. By generating pseudo-labels or enforcing consistency on unlabeled examples, the method extracts supervisory signal from unannotated data, yielding stronger classifiers when ground-truth annotations are scarce.

MethodMind'de açSoonVideoSoon

Tam yöntemi oku

Members only

Sign in with a free account to read this section.

Sign in

Sources

  1. Liu, Y., Ott, M., Goyal, N., Du, J., Joshi, M., Chen, D., Levy, O., Lewis, M., Zettlemoyer, L., & Stoyanov, V. (2019). RoBERTa: A Robustly Optimized BERT Pretraining Approach. arXiv preprint arXiv:1907.11692. link ↗
  2. Xie, Q., Dai, Z., Hovy, E., Luong, M.-T., & Le, Q. V. (2020). Unsupervised Data Augmentation for Consistency Training. Advances in Neural Information Processing Systems (NeurIPS), 33, 11904–11915. link ↗

Related methods

BERT-based ClassificationFine-Tuned RoBERTa-based ClassificationRoBERTa-based ClassificationSemi-supervised BERT-based ClassificationSemi-supervised TransformerWeakly Supervised RoBERTa-based Classification

Referenced by

Weakly Supervised RoBERTa-based Classification

Bu sayfada bir hata mı var? Bildir / düzeltme öner →

ScholarGate — Semi-supervised RoBERTa-based Classification (Semi-supervised RoBERTa-based Text Classification). Retrieved 2026-06-04 from https://scholargate.app/tr/deep-learning/semi-supervised-roberta-based-classification