Transformer ์ ๋ฆฌ ํฌ์คํธ #01๋จผ์ , ๋ ผ๋ฌธ ๋ฆฌ๋ทฐ๋ฅผ ์์์ผ๋ก Tansformer์ Key word๋ฅผ ์ค์ฌ์ผ๋ก ์์ธํ ์ ๋ฆฌํด์ ํฌ์คํ ํด๋ณด๋ ค ํ๋ค.>> ๋ ผ๋ฌธ ๋งํฌ 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.org1. Introduction..