Attention Is All You Need

A Paper A Day: #24 Attention Is All You Need | by Amr Sharaf | Medium

The dominant sequence transduction models are based on complex recurrent or convolutional neural networks that include an encoder and a decoder. 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 41.0 after training for 3.5 days on eight GPUs, a small fraction of the training costs of the best models from the literature.

https://arxiv.org/pdf/1706.03762.pdf

现有的大多数序列转换模型都是基于复杂循环或卷积的具有编码器和解码器架构的神经网络。这些模型之中表现最好的模型使用注意力机制沟通编码器和解码器。我们提出来一种新的简单的神经网络模型:Transformer.这个模型基于注意力机制且完全不同于循环和卷积神经网络。

发表评论

邮箱地址不会被公开。 必填项已用*标注