Paper page - Attention Is All You Need (original) (raw)
Published on Jun 12, 2017
Abstract
The Transformer architecture, based purely on attention mechanisms, achieves superior performance on machine translation and parsing tasks with improved parallelizability and reduced training time.
The dominant sequence transduction models are based on complex recurrent orconvolutional 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-artBLEU 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 theTransformer generalizes well to other tasks by applying it successfully toEnglish constituency parsing both with large and limited training data.
View arXiv page View PDF Add to collection
Models citing this paper205
nvidia/canary-1b Automatic Speech Recognition• UpdatedApr 24 • 11.8k• 432
google/paligemma-3b-pt-224 Image-Text-to-Text• UpdatedSep 21, 2024 • 44.8k• 332
nvidia/canary-1b-flash Automatic Speech Recognition• UpdatedMar 18 • 362k• 212
google/paligemma2-3b-pt-224 Image-Text-to-Text• UpdatedDec 5, 2024 • 155k• 150
Browse 205 models citing this paper
Datasets citing this paper2
bird-of-paradise/transformer-from-scratch-tutorial Updated13 days ago • 182• 9
FcmC/E4SelfLearning UpdatedJun 30, 2024 • 54• 1