方法对比

	弱监督句子嵌入	弱监督BERT分类
领域	深度学习	深度学习
方法族	Machine learning	Machine learning
起源年份	2016–2019	2017–2020
提出者	Ratner et al. (weak supervision framework); Reimers & Gurevych (sentence embeddings)	Multiple (Ratner et al. for weak supervision framework; Meng et al. for BERT integration)
类型	Representation learning under weak supervision	Weakly supervised fine-tuning of pre-trained language model
开创性文献	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.
别名	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
相关	6	6
摘要	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.