During inference in sequence-to-sequence models, each word that the model outputs is fed back as the input word in the next time step to generate an entire sentence until an end token is predicted.
factualpending
Speaker
Unidentified Speaker — 10 years of NLP history explained in 50 concepts | From Wor… [uocYQH0cWTs]Evidence Quote
“during inference we feed e each word that the model outputs back as the input word in the next time step and generate an entire sentence until the end token has been predicted”
Source
10 years of NLP history explained in 50 concepts | From Word2Vec, RNNs to GPT— Neural Breakdown with AVBCreated: 8/11/2026, 1:00:15 AM
Your notes
Loading notes...