방법 비교

	자기 지도 학습 문장 임베딩	Self-supervised Transformer
분야	딥러닝	딥러닝
계열	Machine learning	Machine learning
기원 연도	2019–2021	2017–2019
창시자	Gao, T., Yao, X., & Chen, D. (SimCSE); Reimers, N. & Gurevych, I. (Sentence-BERT)	Vaswani et al. (architecture); Devlin et al. (BERT self-supervised paradigm)
유형	Self-supervised representation learning	Self-supervised deep learning model
원전	Gao, T., Yao, X., & Chen, D. (2021). SimCSE: Simple Contrastive Learning of Sentence Embeddings. Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing (EMNLP), 6894–6910.	Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2019). BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. Proceedings of NAACL-HLT 2019, 4171–4186.
별칭	self-supervised sentence representation learning, contrastive sentence embeddings, SimCSE, unsupervised sentence encoders	SSL Transformer, self-supervised pretraining, masked self-attention pretraining, contrastive transformer
관련	5	5
요약	Self-supervised sentence embeddings train a neural encoder to map sentences into a dense vector space without requiring manually labeled pairs. By constructing positive examples automatically — for instance by passing the same sentence through dropout twice — and using contrastive objectives, the model learns semantically rich representations that transfer well to similarity, retrieval, and classification tasks.	A self-supervised Transformer is a Transformer network pretrained using automatically constructed supervision signals — such as masked token prediction or next-sentence prediction — rather than human-annotated labels. The resulting representations are then fine-tuned or probed on downstream tasks. BERT, GPT, and ViT (Vision Transformer in masked-image modeling mode) are the most widely known instantiations of this paradigm.