Uporedite metode

	Слабо надгледани Трансформер	Slabo nadzirana BERT-bazirana klasifikacija
Oblast	Duboko učenje	Duboko učenje
Porodica	Machine learning	Machine learning
Godina nastanka	2017–2019	2017–2020
Tvorac	Multiple contributors (weak supervision paradigm: Zhou 2018; transformer backbone: Vaswani et al. 2017)	Multiple (Ratner et al. for weak supervision framework; Meng et al. for BERT integration)
Tip	Weakly supervised deep learning	Weakly supervised fine-tuning of pre-trained language model
Temeljni izvor	Ratner, A., Bach, S. H., Ehrenberg, H., Fries, J., Wu, S., & Re, C. (2017). Snorkel: Rapid training data creation with weak supervision. Proceedings of the VLDB Endowment, 11(3), 269–282.	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	WST, weakly supervised attention model, noisy-label transformer, weak supervision with transformers	WS-BERT, BERT with weak supervision, label-efficient BERT classification, noisy-label BERT fine-tuning
Srodne	5	6
Sažetak	Weakly Supervised Transformer combines the representational power of Transformer architectures with weak supervision strategies that exploit noisy, incomplete, or programmatically generated labels — making it possible to train high-quality NLP and vision models when fully annotated datasets are scarce or prohibitively expensive to produce.	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.