Methoden vergleichen

	Schwache BERT-basierte Klassifikation	Semi-überwachte BERT-basierte Klassifikation
Fachgebiet	Deep Learning	Deep Learning
Familie	Machine learning	Machine learning
Entstehungsjahr	2017–2020	2019–2020
Urheber	Multiple (Ratner et al. for weak supervision framework; Meng et al. for BERT integration)	Multiple groups (Xie et al.; Chen et al.; Devlin et al. for BERT base)
Typ	Weakly supervised fine-tuning of pre-trained language model	Semi-supervised fine-tuning of pre-trained transformer
Wegweisende Quelle	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.	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.
Aliasnamen	WS-BERT, BERT with weak supervision, label-efficient BERT classification, noisy-label BERT fine-tuning	Semi-supervised BERT, BERT SSL Classification, BERT with Unlabeled Data, BERT Semi-supervised Fine-tuning
Verwandt	6	6
Zusammenfassung	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.	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.