0. 논문 소개논문 링크[Attention Is All You NeedThe 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 newarxiv.org](https://arxiv.org/abs/1706.03762)1. Abstract기존 최고 성능은 인코더와 디코더를 사용한 복잡한 모델, 또는 CNN 기반 모델새로운 아..
