LINEAiGE
AI HISTORY

Efficient Estimation of Word Representations in Vector Space

Tomas Mikolov, Kai Chen, Greg Corrado, and Jeffrey Dean submitted Efficient Estimation of Word Representations in Vector Space to arXiv on January 16, 2013, describing two model architectures for learning continuous vector representations of words from very large data sets.

January 16, 2013AI HISTORYVERIFIED

Historical classification

This verified record belongs to LINEAiGE's artificial-intelligence history layer beginning in 1956.

Why it matters

A documented word-representation and natural-language-processing milestone associated with efficient neural word-embedding methods.

People, organizations & technologies

PEOPLE
Tomas Mikolov, Kai Chen, Greg Corrado, Jeffrey Dean

ORGANIZATIONS
Google

TECHNOLOGIES
Word embeddings, Continuous word representations, Natural language processing

Evidence & verification

STATE
verified

CONFIDENCE
high

LAST VERIFIED
2026-09-08T08:50:00+08:00

The original arXiv record establishes the title, authors, submission date of January 16 2013, and the paper's proposal of two architectures for learning continuous vector word representations from large data sets. Google Research independently preserves the publication and abstract. This record is a publication/submission milestone and does not infer a separate software-release date, geography, ancestry, influence, or causal relationship.

Sources

SOURCE 1 · PRIMARY · CLAIM-EVIDENCE

Efficient Estimation of Word Representations in Vector Space

arXiv

PUBLISHED
2013-01-16

SOURCE 2 · CORROBORATION

Efficient Estimation of Word Representations in Vector Space

Google Research

Trace the chronology

Record identity

LINEAiGE ID
word2vec-2013