t5-text-to-text-framing
IN premise — entries/2026/06/21/wiki-Transformer_deep_learning_architecture-chunk-6.md
Created 2026-06-21T09:50:10+00:00
T5 (Raffel et al., 2020) is an encoder-decoder Transformer that frames all NLP tasks (classification, translation, summarization) as text-to-text sequence generation.
Summary
T5 is a single Transformer model that handles a wide range of language tasks — classification, translation, summarization, and more — by treating each one simply as "read some text, write some text," so you never need a separate architecture per task. This matters because it collapses a long toolbox of specialized models into one unified pipeline, meaning new language tasks can often be added just by reformatting their inputs and outputs as text rather than designing new components from scratch.