0. 논문 소개 논문 링크 [Attention Is All You Need 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 arxiv.org](https://arxiv.org/abs/1706.03762) 1. Abstract 기존 최고 성능은 인코더와 디코더를 사용한 복잡한 모델, 또는 CNN 기반 모..