Usporedite metode

	Polu-nadzirana klasifikacija temeljena na BERT-u	Klasifikacija temeljena na BERT-u uz slabi nadzor
Područje	Duboko učenje	Duboko učenje
Obitelj	Machine learning	Machine learning
Godina nastanka	2019–2020	2017–2020
Tvorac	Multiple groups (Xie et al.; Chen et al.; Devlin et al. for BERT base)	Multiple (Ratner et al. for weak supervision framework; Meng et al. for BERT integration)
Vrsta	Semi-supervised fine-tuning of pre-trained transformer	Weakly supervised fine-tuning of pre-trained language model
Temeljni izvor	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.	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.
Drugi nazivi	Semi-supervised BERT, BERT SSL Classification, BERT with Unlabeled Data, BERT Semi-supervised Fine-tuning	WS-BERT, BERT with weak supervision, label-efficient BERT classification, noisy-label BERT fine-tuning
Srodne	6	6
Sažetak	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.	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.