השוואת שיטות

	LSTM מפוקח-בקושי	טרנספורמר עם פיקוח חלש
תחום	למידה עמוקה	למידה עמוקה
משפחה	Machine learning	Machine learning
שנת המקור	2016–2018	2017–2019
הוגה השיטה	Ratner et al. (data programming framework); Hochreiter & Schmidhuber (LSTM backbone)	Multiple contributors (weak supervision paradigm: Zhou 2018; transformer backbone: Vaswani et al. 2017)
סוג	Weakly supervised sequence model	Weakly supervised deep learning
מקור מכונן	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., Bach, S. H., Ehrenberg, H., Fries, J., Wu, S., & Re, C. (2017). Snorkel: Rapid training data creation with weak supervision. Proceedings of the VLDB Endowment, 11(3), 269–282.
כינויים	WS-LSTM, noisy-label LSTM, distant-supervision LSTM, data-programming LSTM	WST, weakly supervised attention model, noisy-label transformer, weak supervision with transformers
קשורות	6	5
תקציר	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.	Weakly Supervised Transformer combines the representational power of Transformer architectures with weak supervision strategies that exploit noisy, incomplete, or programmatically generated labels — making it possible to train high-quality NLP and vision models when fully annotated datasets are scarce or prohibitively expensive to produce.