Porovnat metody

	Slabě supervizovaná klasifikace založená na BERT	Klasifikace založená na RoBERTa
Obor	Hluboké učení	Hluboké učení
Rodina	Machine learning	Machine learning
Rok vzniku	2017–2020	2019
Tvůrce	Multiple (Ratner et al. for weak supervision framework; Meng et al. for BERT integration)	Liu, Y. et al. (Facebook AI Research / University of Washington)
Typ	Weakly supervised fine-tuning of pre-trained language model	Pre-trained transformer fine-tuned for sequence classification
Původní zdroj	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.	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.
Další názvy	WS-BERT, BERT with weak supervision, label-efficient BERT classification, noisy-label BERT fine-tuning	RoBERTa classifier, RoBERTa text classification, Robustly Optimized BERT Classification, RoBERTa fine-tuning for classification
Příbuzné	6	5
Shrnutí	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.	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.