So sánh phương pháp

	Transformer tự giám sát	Nhúng câu (Sentence Embeddings)
Lĩnh vực	Học sâu	Học sâu
Họ	Machine learning	Machine learning
Năm ra đời	2017–2019	2015–2019
Người khởi xướng	Vaswani et al. (architecture); Devlin et al. (BERT self-supervised paradigm)	Kiros et al. (Skip-Thought, 2015); Reimers & Gurevych (Sentence-BERT, 2019)
Loại	Self-supervised deep learning model	Representation learning / embedding
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.	Reimers, N., & Gurevych, I. (2019). Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks. Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing (EMNLP), 3980–3990.
Tên gọi khác	SSL Transformer, self-supervised pretraining, masked self-attention pretraining, contrastive transformer	sentence vectors, sentence representations, SBERT, semantic sentence encoding
Liên quan	5	4
Tóm tắt	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.	Sentence Embeddings convert a sentence or short text into a single fixed-length dense vector that captures its semantic meaning. These vectors allow downstream tasks — semantic similarity, clustering, retrieval, and classification — to operate on numerical representations instead of raw text, making them one of the most versatile building blocks in modern NLP pipelines.