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 Basilico

Evidence 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.”

Source

Jeff Dean (Google): Exciting Trends in Machine Learning— Rice Ken Kennedy Institute
Created: 8/11/2026, 1:28:51 AM

Your notes

Loading notes...