方法对比

	半监督句子嵌入	半监督式BERT分类
领域	深度学习	深度学习
方法族	Machine learning	Machine learning
起源年份	2019–2021	2019–2020
提出者	Gao, T.; Reimers, N. et al. (multiple contributors)	Multiple groups (Xie et al.; Chen et al.; Devlin et al. for BERT base)
类型	Semi-supervised representation learning	Semi-supervised fine-tuning of pre-trained transformer
开创性文献	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.	Xie, Q., Dai, Z., Hovy, E., Luong, T., & Le, Q. (2020). Unsupervised Data Augmentation for Consistency Training. Advances in Neural Information Processing Systems (NeurIPS), 33, 27780–27792.
别名	Semi-supervised SimCSE, Self-training sentence encoders, Pseudo-labeled sentence representation learning, SSL sentence embeddings	Semi-supervised BERT, BERT SSL Classification, BERT with Unlabeled Data, BERT Semi-supervised Fine-tuning
相关	5	6
摘要	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.	Semi-supervised BERT-based classification fine-tunes a pre-trained BERT encoder on a small pool of labeled text examples while simultaneously leveraging a much larger body of unlabeled text — via consistency training, pseudo-labeling, or data augmentation — to produce high-quality classifiers even when manual annotation is scarce.