Sequence-to-sequence models use an encoder-decoder architecture where an encoder processes input sequences (e.g., English text) into a learned representation, which initializes a decoder that generates output sequences (e.g., French translation) one word at a time, and scaling this approach yields major improvements in translation accuracy.
factualpending
Speaker
Justin BasilicoEvidence Quote
“use a neural encoder over this input sequence to initialize the state... use that to initialize the state of the neural decoder. You scale this up and it works. You get major improvements in translation accuracy.”
Created: 8/11/2026, 1:28:51 AM
Your notes
Loading notes...