So sánh phương pháp

	Transformer bán giám sát	Transformer tự giám sát
Lĩnh vực	Học sâu	Học sâu
Họ	Machine learning	Machine learning
Năm ra đời	2018–2019	2017–2019
Người khởi xướng	Devlin, J. et al. (BERT); broader SSL-Transformer paradigm community	Vaswani et al. (architecture); Devlin et al. (BERT self-supervised paradigm)
Loại	Semi-supervised deep learning	Self-supervised deep learning model
Công trình gốc	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.	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.
Tên gọi khác	semi-supervised transformer model, SSL transformer, transformer with self-supervised pre-training, semi-supervised attention model	SSL Transformer, self-supervised pretraining, masked self-attention pretraining, contrastive transformer
Liên quan	5	5
Tóm tắt	Semi-supervised learning with Transformer architectures leverages large quantities of unlabeled data alongside a small labeled set to train powerful sequence models. The dominant pattern — exemplified by BERT — first pre-trains the Transformer on unlabeled data using self-supervised objectives such as masked token prediction, then fine-tunes it on the labeled task. This two-stage approach dramatically reduces the labeled data needed to achieve strong performance.	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.