手法を比較

	弱教師あり文埋め込み	半教師あり文埋め込み
分野	深層学習	深層学習
系統	Machine learning	Machine learning
提唱年	2016–2019	2019–2021
提唱者	Ratner et al. (weak supervision framework); Reimers & Gurevych (sentence embeddings)	Gao, T.; Reimers, N. et al. (multiple contributors)
種類	Representation learning under weak supervision	Semi-supervised representation learning
原典	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.	Gao, T., Yao, X., & Chen, D. (2021). SimCSE: Simple Contrastive Learning of Sentence Embeddings. In Proceedings of EMNLP 2021 (pp. 6894–6910). Association for Computational Linguistics.
別名	WS sentence embeddings, noisy-label sentence representation learning, weakly supervised sentence representation, distant-supervision sentence embeddings	Semi-supervised SimCSE, Self-training sentence encoders, Pseudo-labeled sentence representation learning, SSL sentence embeddings
関連	6	5
概要	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.	Semi-supervised sentence embeddings combine a small set of labeled sentence pairs with large quantities of unlabeled text to train dense vector representations of sentences. By exploiting abundant unlabeled data through contrastive objectives or pseudo-labeling, these models produce high-quality embeddings for semantic similarity, retrieval, and classification even when annotated data is scarce.