Attention Is All You Need

TL;DR

The paper introduces the Transformer, a novel neural network architecture based solely on attention mechanisms, which outperforms previous models in machine translation and generalizes well to other NLP tasks, while being more efficient to train.

Contribution

The Transformer architecture eliminates recurrence and convolutions, achieving superior translation quality and training efficiency, and demonstrates versatility across different NLP tasks.

Findings

Achieved 28.4 BLEU on WMT 2014 English-German translation.

Set a new state-of-the-art BLEU score of 41.8 on WMT 2014 English-French translation.

Requires significantly less training time compared to previous models.

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.