方法对比

	半监督Word2Vec	自监督Word2Vec
领域	深度学习	深度学习
方法族	Machine learning	Machine learning
起源年份	2013–2015	2013
提出者	Mikolov, T. et al. (Word2Vec); semi-supervised framing via Collobert & Weston and subsequent NLP literature	Mikolov, T., Chen, K., Corrado, G., & Dean, J.
类型	Semi-supervised representation learning	Self-supervised neural word embedding
开创性文献	Mikolov, T., Chen, K., Corrado, G., & Dean, J. (2013). Efficient Estimation of Word Representations in Vector Space. In Proceedings of ICLR 2013.	Mikolov, T., Chen, K., Corrado, G., & Dean, J. (2013). Efficient estimation of word representations in vector space. In Proceedings of the International Conference on Learning Representations (ICLR 2013).
别名	Word2Vec with semi-supervised learning, semi-supervised word embeddings, Word2Vec SSL, unsupervised pretraining with Word2Vec	Word2Vec, word embeddings, Skip-gram model, CBOW model
相关	6	3
摘要	Semi-supervised Word2Vec trains dense word representations on a large unlabeled corpus using Word2Vec (skip-gram or CBOW), then uses those embeddings as fixed or fine-tunable input features for a downstream classifier trained on a small labeled dataset. This two-stage process lets models benefit from abundant unlabeled text when labeled data is scarce.	Word2Vec is a shallow neural network model introduced by Mikolov et al. (2013) that learns dense vector representations of words from large unlabeled text corpora using self-supervised objectives. By training a model to predict surrounding context words (Skip-gram) or a target word from its context (CBOW), it captures rich semantic and syntactic regularities in continuous vector space without any manual annotation.