So sánh phương pháp

	Nhúng câu giám sát yếu	Phân loại dựa trên BERT với Giám sát Yếu
Lĩnh vực	Học sâu	Học sâu
Họ	Machine learning	Machine learning
Năm ra đời	2016–2019	2017–2020
Người khởi xướng	Ratner et al. (weak supervision framework); Reimers & Gurevych (sentence embeddings)	Multiple (Ratner et al. for weak supervision framework; Meng et al. for BERT integration)
Loại	Representation learning under weak supervision	Weakly supervised fine-tuning of pre-trained language model
Công trình gốc	Ratner, A., De Sa, C., Wu, S., Selsam, D., & Re, C. (2016). Data Programming: Creating Large Training Sets, Quickly. Advances in Neural Information Processing Systems (NeurIPS), 29.	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.
Tên gọi khác	WS sentence embeddings, noisy-label sentence representation learning, weakly supervised sentence representation, distant-supervision sentence embeddings	WS-BERT, BERT with weak supervision, label-efficient BERT classification, noisy-label BERT fine-tuning
Liên quan	6	6
Tóm tắt	Weakly supervised sentence embeddings train dense sentence representations using noisy, heuristic, or programmatically generated labels instead of costly human annotation. Labeling functions — rules, distant supervision signals, or lightweight classifiers — supply approximate supervision that a label model aggregates into probabilistic labels, which then guide the sentence encoder to produce task-useful representations at scale.	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.