Machine learningDeep learning / NLP / CV
半监督式 Transformer
半监督式 Transformer 架构利用大量无标注数据和少量有标注数据进行强大的序列模型训练。其主导模式——以 BERT 为例——首先使用自监督目标（如掩码词预测）在无标注数据上预训练 Transformer，然后针对有标注任务进行微调。这种两阶段方法可显著减少实现强性能所需的有标注数据量。
阅读完整方法
仅限会员
登录使用免费账户登录即可阅读本节。
Method map
The neighbourhood of related methods — select a node to explore.
+5 more
来源
- 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. DOI: 10.18653/v1/N19-1423 ↗
- Zoph, B., Ghiasi, G., Lin, T.-Y., Cui, Y., Liu, H., Cubuk, E. D., & Le, Q. V. (2020). Rethinking Pre-training and Self-training. Advances in Neural Information Processing Systems (NeurIPS), 33, 3833–3845. link ↗
如何引用本页
ScholarGate. (2026, June 3). Semi-supervised Learning with Transformer Architectures. ScholarGate. https://scholargate.app/zh/deep-learning/semi-supervised-transformer
Which method?
Set this method beside its closest kin and read them side by side — the library lays the books on the table; the choice is yours.
- [需翻译标题：BERT-based Classification...]深度学习↔ compare
- 微调Transformer深度学习↔ compare
- 基于RoBERTa的分类深度学习↔ compare
- 自监督Transformer深度学习↔ compare
- 半监督卷积神经网络深度学习↔ compare