Porovnať metódy

	Polosupervizovaná klasifikácia založená na modeli BERT	Klasifikácia založená na RoBERTa
Odbor	Hlboké učenie	Hlboké učenie
Rodina	Machine learning	Machine learning
Rok vzniku	2019–2020	2019
Tvorca	Multiple groups (Xie et al.; Chen et al.; Devlin et al. for BERT base)	Liu, Y. et al. (Facebook AI Research / University of Washington)
Typ	Semi-supervised fine-tuning of pre-trained transformer	Pre-trained transformer fine-tuned for sequence classification
Pôvodný zdroj	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.	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.
Ďalšie názvy	Semi-supervised BERT, BERT SSL Classification, BERT with Unlabeled Data, BERT Semi-supervised Fine-tuning	RoBERTa classifier, RoBERTa text classification, Robustly Optimized BERT Classification, RoBERTa fine-tuning for classification
Príbuzné	6	5
Zhrnutie	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.	RoBERTa-based Classification applies the RoBERTa pre-trained transformer — trained more robustly than BERT with dynamic masking and larger batches — to text categorisation tasks by adding a lightweight classification head on top of the [CLS] token representation and fine-tuning the entire model on labelled examples. It consistently matches or outperforms BERT on standard NLP benchmarks.