Usporedite metode

	Klasifikacija temeljena na BERT-u uz slabi nadzor	Fino podešena klasifikacija temeljena na BERT-u
Područje	Duboko učenje	Duboko učenje
Obitelj	Machine learning	Machine learning
Godina nastanka	2017–2020	2019
Tvorac	Multiple (Ratner et al. for weak supervision framework; Meng et al. for BERT integration)	Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (Google AI)
Vrsta	Weakly supervised fine-tuning of pre-trained language model	Pre-trained transformer fine-tuned for classification
Temeljni izvor	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.	Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2019). BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. Proceedings of NAACL-HLT 2019, 4171–4186.
Drugi nazivi	WS-BERT, BERT with weak supervision, label-efficient BERT classification, noisy-label BERT fine-tuning	BERT fine-tuning, BERT classifier, fine-tuned BERT, BERT sequence classification
Srodne	6	5
Sažetak	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.	Fine-Tuned BERT-based Classification adapts a pre-trained BERT transformer to a specific text classification task by adding a lightweight output layer and continuing gradient-based training on labelled examples. It consistently achieves near-state-of-the-art accuracy on sentiment analysis, topic categorisation, intent detection, and other NLP classification tasks with relatively small labelled datasets.