方法对比

	弱监督 LSTM	半监督长短期记忆网络 (Semi-supervised LSTM)
领域	深度学习	深度学习
方法族	Machine learning	Machine learning
起源年份	2016–2018	2015–2018
提出者	Ratner et al. (data programming framework); Hochreiter & Schmidhuber (LSTM backbone)	Hochreiter, S. & Schmidhuber, J. (LSTM); semi-supervised extensions by various authors (2015–2020)
类型	Weakly supervised sequence model	Semi-supervised sequence 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.	Hochreiter, S., & Schmidhuber, J. (1997). Long Short-Term Memory. Neural Computation, 9(8), 1735–1780.
别名	WS-LSTM, noisy-label LSTM, distant-supervision LSTM, data-programming LSTM	SSL-LSTM, semi-supervised sequence model, LSTM with unlabeled data, pseudo-label LSTM
相关	6	3
摘要	Weakly supervised LSTM trains a Long Short-Term Memory network on sequence data where clean, manually annotated labels are scarce or absent. Instead, multiple imperfect label sources — heuristic rules, distant supervision, crowdsourcing, or programmatic labeling functions — are combined to produce probabilistic training labels, which are then used to supervise the LSTM. This allows scalable training on large unlabeled corpora without exhaustive human annotation.	Semi-supervised LSTM combines the sequential memory of Long Short-Term Memory networks with semi-supervised learning strategies — using a small labeled dataset alongside a large pool of unlabeled sequences. The model is pretrained or regularized on unlabeled data, then fine-tuned on labeled examples, delivering strong generalization when labeled data is scarce.