Attention Is All You Need

The Transformer replaces recurrence and convolutions with attention, achieving superior translation quality and faster training.

Ashish Vaswani, Noam Shazeer, Niki Jitendra Parmar, Jakob Uszkoreit, Llion Jones, Aidan N. Gomez, Łukasz Kaiser, Illia Polosukhin

Published Aug 23, 202526,828 citationsPaper ↗

91%

OverallMust read

OverallMust readVote to see the scoreThe exact score shows once you've voted, so every vote is your own call. The first half of each home page shelf shows its scores.

Readers

–

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel18/21reviewers recommend it

lenient 5/5

medium 9/11

strict 4/5

AI panel?Vote to see what the 20 AI reviewers said

Panel consensus

The Transformer establishes a pedagogically elegant, structurally dominant architecture that kills recurrence with pure global attention and delivers landmark translation results, though critics contend its gains rely heavily on massive parallel compute rather than a fully…

Abstract

The dominant sequence transduction models are based on complex recurrent or convolutional neural networks in an encoder-decoder configuration. The best performing models also connect the encoder and decoder through an attention mechanism. We propose a new simple network architecture, the Transformer, based solely on attention mechanisms, dispensing with recurrence and convolutions entirely. Experiments on two machine translation tasks show these models to be superior in quality while being more parallelizable and requiring significantly less time to train. Our model achieves 28.4 BLEU on the WMT 2014 English-to-German translation task, improving over the existing best results, including ensembles by over 2 BLEU. On the WMT 2014 English-to-French translation task, our model establishes a new single-model state-of-the-art BLEU score of 41.8 after training for 3.5 days on eight GPUs, a small fraction of the training costs of the best models from the literature. We show that the Transformer generalizes well to other tasks by applying it successfully to English constituency parsing both with large and limited training data.