方法对比

	BERT 嵌入	Word2Vec
领域	文本挖掘	文本挖掘
方法族	Process / pipeline	Process / pipeline
起源年份	2019	2013
提出者	Devlin, Chang, Lee & Toutanova (Google AI)	Tomas Mikolov et al.
类型	Contextual transformer text-representation method	Neural word-embedding model
开创性文献	Devlin, J., Chang, M.-W., Lee, K. & Toutanova, K. (2019). BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. NAACL-HLT, 4171-4186.	Mikolov, T., Chen, K., Corrado, G. & Dean, J. (2013). Efficient Estimation of Word Representations in Vector Space.
别名	contextual embeddings, transformer embeddings, BERT Tabanlı Metin Gömülmeleri	word embeddings, skip-gram, continuous bag-of-words, Word2Vec Kelime Gömülmeleri
相关	4	4
摘要	BERT-based text embeddings, introduced by Devlin and colleagues at Google AI in 2019, turn text into context-sensitive dense vectors using a bidirectional Transformer encoder. Because the meaning of a word shifts with its context, BERT produces richer representations than static methods such as Word2Vec or topic models like LDA.	Word2Vec is a neural word-embedding technique introduced by Mikolov and colleagues in 2013 that maps each word in a text corpus to a dense numeric vector. Words that appear in similar contexts end up close together in the vector space, so the embeddings capture semantic similarity that can be measured arithmetically.