Porovnať metódy

	Klasifikácia založená na RoBERTa so slabým dohľadom	Polosupervizované klasifikovanie založené na RoBERTa
Odbor	Hlboké učenie	Hlboké učenie
Rodina	Machine learning	Machine learning
Rok vzniku	2019–2020	2019–2020
Tvorca	Liu et al. (RoBERTa, 2019); weak supervision paradigm: Ratner et al. (2016–2020)	Liu et al. (RoBERTa, 2019); semi-supervised adaptation by the NLP community
Typ	Pretrained transformer classifier with weak supervision	Semi-supervised fine-tuning of a pretrained language model
Pôvodný 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:1907.11692.	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	WS-RoBERTa, RoBERTa with weak supervision, weakly supervised transformer classification, noisy-label RoBERTa classifier	Semi-supervised RoBERTa, RoBERTa with semi-supervised learning, SSL-RoBERTa classification, RoBERTa pseudo-label classification
Príbuzné	5	6
Zhrnutie	Weakly supervised RoBERTa-based classification combines the RoBERTa pretrained transformer with weak supervision — programmatic or heuristic labeling sources — to train powerful text classifiers without requiring a fully hand-labeled dataset. Labeling functions, distant supervision, or crowd-sourced signals generate noisy labels that are aggregated and used to fine-tune RoBERTa for downstream classification tasks.	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.