Porovnat metody

	Polo-dohledová klasifikace založená na RoBERTa	Polu-dohledová klasifikace založená na BERT
Obor	Hluboké učení	Hluboké učení
Rodina	Machine learning	Machine learning
Rok vzniku	2019–2020	2019–2020
Tvůrce	Liu et al. (RoBERTa, 2019); semi-supervised adaptation by the NLP community	Multiple groups (Xie et al.; Chen et al.; Devlin et al. for BERT base)
Typ	Semi-supervised fine-tuning of a pretrained language model	Semi-supervised fine-tuning of pre-trained transformer
Původní zdroj	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.	Xie, Q., Dai, Z., Hovy, E., Luong, T., & Le, Q. (2020). Unsupervised Data Augmentation for Consistency Training. Advances in Neural Information Processing Systems (NeurIPS), 33, 27780–27792.
Další názvy	Semi-supervised RoBERTa, RoBERTa with semi-supervised learning, SSL-RoBERTa classification, RoBERTa pseudo-label classification	Semi-supervised BERT, BERT SSL Classification, BERT with Unlabeled Data, BERT Semi-supervised Fine-tuning
Příbuzné	6	6
Shrnutí	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.	Semi-supervised BERT-based classification fine-tunes a pre-trained BERT encoder on a small pool of labeled text examples while simultaneously leveraging a much larger body of unlabeled text — via consistency training, pseudo-labeling, or data augmentation — to produce high-quality classifiers even when manual annotation is scarce.