Attention Is All You Need
No Thumbnail Available
Date
2017-06-12
Journal Title
Journal ISSN
Volume Title
Publisher
arXiv
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.
Description
이 논문은 순차적인 데이터를 처리하는 데 있어 기존 RNN 또는 CNN 기반의 구조 없이, Self-Attention 메커니즘만을 활용한 Transformer 모델을 제안한다. 제안된 모델은 기계 번역에서 뛰어난 성능을 보여주며 이후 많은 언어 모델(BERT, GPT 등)의 기반이 되었다.
© 2017 The Authors. Licensed under arXiv.org policies.
Keywords
Transformer, Self-Attention, NLP, Neural Networks, Machine Translation