Back to timeline

Research · January 2013

word2vec

Mikolov and co-authors simplified the neural language model enough that word vectors could be trained on billions of words in hours.

Why it matters

Word vectors went from a research curiosity to an everyday tool available to anyone with a laptop.

The key was removing the hidden layer and replacing the full softmax with approximations. The best-known result is arithmetic on vectors: king minus man plus woman gives queen. That made visible what the model learns is the structure of meaning, not only co-occurrence statistics. The toolkit spread instantly and was the first step toward the representations BERT was later built on.

Event record

Event date
January 2013
Timeline date
Event date
Verification
Sources gathered automatically · September 17, 2026
Lines
ID
evt-0223

Preprint of 16 January 2013; the toolkit was released the same year.

Sources

Related events

Records that link to this one