方法对比

	弱监督循环神经网络	弱监督 LSTM
领域	深度学习	深度学习
方法族	Machine learning	Machine learning
起源年份	2009–2016	2016–2018
提出者	Broadly attributed to the weak supervision / distant supervision research community (Mintz et al., 2009; Ratner et al., 2016)	Ratner et al. (data programming framework); Hochreiter & Schmidhuber (LSTM backbone)
类型	Supervised learning under noisy or incomplete labels	Weakly 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.	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.
别名	WS-RNN, distantly supervised RNN, noise-tolerant RNN, weakly supervised sequence model	WS-LSTM, noisy-label LSTM, distant-supervision LSTM, data-programming LSTM
相关	5	6
摘要	A weakly supervised RNN trains a recurrent neural network on sequences whose labels come from imperfect sources — heuristic rules, distant supervision, crowdsourcing, or generative label models — rather than expensive expert annotation. This lets researchers exploit large unlabeled corpora for sequential tasks such as text classification, named entity recognition, or time-series prediction when fully annotated data is scarce or costly.	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.