Сравнение методов

	Слабо контролируемая классификация на основе RoBERTa	Классификация на основе дообученной модели RoBERTa
Область	Глубокое обучение	Глубокое обучение
Семейство	Machine learning	Machine learning
Год появления	2019–2020	2019
Автор метода	Liu et al. (RoBERTa, 2019); weak supervision paradigm: Ratner et al. (2016–2020)	Liu, Y. et al. (Meta AI / University of Washington)
Тип	Pretrained transformer classifier with weak supervision	Pretrained transformer fine-tuned for classification
Основополагающий источник	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:1907.11692.
Другие названия	WS-RoBERTa, RoBERTa with weak supervision, weakly supervised transformer classification, noisy-label RoBERTa classifier	RoBERTa fine-tuning, RoBERTa classifier, fine-tuned RoBERTa, RoBERTa sequence classification
Связанные	5	5
Сводка	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.	Fine-tuned RoBERTa-based classification adapts the RoBERTa pretrained transformer — itself a robustly retrained variant of BERT — to a specific text classification task by appending a classification head and continuing training on labeled examples. It consistently achieves state-of-the-art or near-state-of-the-art performance on sentiment analysis, topic classification, toxicity detection, and similar NLP tasks.