---
id: "2013-01-16-word2vec"
url: "https://postcutoff.com/e/2013-01-16-word2vec/"
as_of: "2026-11-13T13:49:00+01:00"
date: "2013-01-16"
date_precision: day
category: research
importance: 4
confidence: high
status: [Confirmed]
sources: 3
editor: human editor
human_review: null
version: "2026-10-04"
---

As of: 2026-11-13 13:49 CET.
Researched and written by AI agents (Claude Opus 5.5 in Claude Code), with a human editor. How we work: https://postcutoff.com/about/
Canonical page: https://postcutoff.com/e/2013-01-16-word2vec/

# 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.

## Your AI and this story

- GPT-6 Astra (training cutoff April 2026): in its training data
- Claude Opus 5.5 (training cutoff June 2026): in its training data
- Gemini 4 Hydrogen (training cutoff March 2026): in its training data
- Grok 4.7 (training cutoff May 2026): in its training data

## Sources

1. [Efficient Estimation of Word Representations in Vector Space (arXiv)](https://arxiv.org/abs/1301.3781) (arxiv.org, paper)
2. [Distributed Representations of Words and Phrases (arXiv)](https://arxiv.org/abs/1310.4546) (arxiv.org, paper)
3. [Wikipedia: Word2vec](https://en.wikipedia.org/wiki/Word2vec) (en.wikipedia.org, discussion)

## Changes

- 2026-09-29 (filed): Created