Mikolov and colleagues: efficient word-vector estimation

What changed

Large-corpus word embeddings became cheaper to train while retaining useful linguistic relationships.

Scientific scope

January 2013 four-author paper; later negative sampling, phrase extensions and software ecosystem are distinct.

Evidence

The linked sources identify this contribution and its scope. WRS has not independently reconstructed the scientific claims. The record is the January 2013 four-author paper. The word2vec software, negative sampling, phrase extensions and other distributional-embedding traditions require separate attribution.

Contributors

• Tomas Mikolov · SCIENCE: Named source author of the scoped work; individual effort shares are not measured.
• Kai Chen · SCIENCE: Named source author of the scoped work; individual effort shares are not measured.
• Greg Corrado · SCIENCE: Named source author of the scoped work; individual effort shares are not measured.
• Jeffrey Dean · SCIENCE: Named source author of the scoped work; individual effort shares are not measured.

• Mikolov et al., Efficient Estimation of Word Representations in Vector Space

Provisional WRS assessment, edition 2026-10-16.1. Independent expert calibration is pending. This grade does not certify correctness or assign ownership.

Full scientific record · Browse contribution grades · Request a correction