word2vec: efficient word embeddings from Google
Tomas Mikolov and colleagues at Google introduced word2vec (CBOW and skip-gram), which learned dense word vectors capturing semantic relationships like king − man + woman ≈ queen.
Key facts
- arXiv 1301.3781 'Efficient Estimation of Word Representations in Vector Space' (January 2013)
- Follow-up NeurIPS 2013 paper added negative sampling
- Open-source C implementation released by Google
- Won the NeurIPS 2023 Test of Time award
What happened
Simple shallow networks trained on billions of words produced embeddings where vector arithmetic reflected meaning.
Why it matters
Popularized learned embeddings, a core building block of all subsequent NLP including Transformers and LLMs.
Changelog
- 2026-09-29: created
Sources (3)
- paperEfficient Estimation of Word Representations in Vector Space (arXiv)
- paperDistributed Representations of Words and Phrases (arXiv)
- discussionWikipedia: Word2vec
id: 2013-01-16-word2vec · updated 2026-09-29 · open in the interactive timeline