{"version":"1.0","type":"rich","provider_name":"Yank","provider_url":"https://yank.info","title":"“We propose the Transformer, the first transduction model relying entirely on self-attention to compute representations of its input and output without using sequence-aligned RNNs or convolution.” — arxiv.org","author_name":"arxiv.org","html":"
\n

“We propose the Transformer, the first transduction model relying entirely on self-attention to compute representations of its input and output without using sequence-aligned RNNs or convolution.”

\n \n
\n","width":640,"height":240,"cache_age":86400}