SESKStuff Everyone Should Know
SESK: Stuff Everyone Should Know · sesk.info/ai-transformer-2017-paper

Which 2017 paper introduced the Transformer architecture?

It was Attention Is All You Need.

Start playing free

  1. Attention Is All You Need ✔
  2. Denoising Diffusion
  3. Generative Adversarial Nets

Why: Vaswani and seven coauthors submitted Attention Is All You Need in June 2017. The paper proposed the architecture now called the Transformer.

Huh, didn't know that: The paper first demonstrated the architecture on machine translation and English constituency parsing.

The dad joke
The Transformer paper got attention without shouting.
Like this card?
Play the game

References

Answer: Attention Is All You Need. Vaswani and seven coauthors submitted Attention Is All You Need in June 2017. The paper proposed the architecture now called the Transformer.

  1. Attention Is All You Need arxiv.org/abs/1706.03762
    Submitted on 12 Jun 2017
    Checked 2026-10-10.

Think this answer is wrong? Tap "Challenge this answer" on the card in the game and tell us why.

Test yourself in the game

Artificial IntelligenceWhich two sequence mechanisms did the original Transformer dispense with?Artificial IntelligenceAfter query-key scores become weights, what does attention combine?Artificial IntelligenceBy what quantity does scaled dot-product attention divide query-key dot products?

That's stuff everyone should know.