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 simple network architecture, the Transformer, based solely on attention mechanisms, dispensing with recurrence and convolutions entirely.
Extract authors, key findings, references, and an executive summary using AI.
No extraction yet
Attach a PDF to this publication first, or provide a PDF URL when extracting.