Machine learningDeep learning / NLP / CV
半监督Word2Vec
半监督Word2Vec使用Word2Vec（skip-gram或CBOW）在大型无标签语料库上训练密集词表示，然后将这些嵌入作为固定或可微调的输入特征，用于在小型有标签数据集上训练的下游分类器。这种两阶段过程使模型能够在有标签数据稀缺时，从丰富的无标签文本中受益。
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.
来源
- Mikolov, T., Chen, K., Corrado, G., & Dean, J. (2013). Efficient Estimation of Word Representations in Vector Space. In Proceedings of ICLR 2013. link ↗
- Collobert, R., Weston, J., Bottou, L., Karlen, M., Kavukcuoglu, K., & Kuksa, P. (2011). Natural Language Processing (Almost) from Scratch. Journal of Machine Learning Research, 12, 2493–2537. link ↗
如何引用本页
ScholarGate. (2026, June 3). Semi-supervised Learning with Word2Vec Word Embeddings. ScholarGate. https://scholargate.app/zh/deep-learning/semi-supervised-word2vec
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.
- 微调 Word2Vec (Fine-Tuned Word2Vec)深度学习↔ compare
- LDA主题模型深度学习↔ compare
- 自监督Word2Vec深度学习↔ compare
- 半监督式BERT分类深度学习↔ compare
- 句子嵌入深度学习↔ compare
- 基于Word2Vec的迁移学习深度学习↔ compare