C Self-attention Additive Dot-product W C= q·k tanh y Wq Wk Wq 15Self-attention 𝑊𝑞 𝑊𝑘 Dot-product 𝛼 𝒒 𝒌 = 𝒒 ∙ 𝒌 Additive 𝑊𝑞 𝑊𝑘 𝛼 + 𝑡𝑎𝑛ℎ 𝑊 15