Methods › Natural Language Processing › Autoencoding Transformers › T5

T5

708 papers tagged archive 2025-07-28

Introduced by Colin Raffel et al. in Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer

archive 2025-07-28 Description, source and code snippet are the archive's method entry.

T5, or Text-to-Text Transfer Transformer, is a Transformer based architecture that uses a text-to-text approach. Every task – including translation, question answering, and classification – is cast as feeding the model text as input and training it to generate some target text. This allows for the use of the same model, loss function, hyperparameters, etc. across our diverse set of tasks. The changes compared to BERT include:

PaperSource

Papers archive 2025-07-28

30 shown of 708, newest first. Repository counts are the archive's code-links table. A Syntology line states what Syntology ran from that paper's harvested code; it is per sample and not a correctness claim.

Tasks archive 2025-07-28

20 shown of 472 tasks the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.

TaskPapers
Language Modelling125
Language Modeling98
Question Answering84
Decoder79
Text Generation65
Sentence56
Translation45
Retrieval40
Transfer Learning40
Machine Translation39
Natural Language Understanding29
Abstractive Text Summarization24
Semantic Parsing23
Sentiment Analysis22
Natural Language Inference20
Code Generation19
Data Augmentation19
Text Summarization19
Diversity18
Large Language Model18

Usage over time archive 2025-07-28

Papers per year tagged with T5: 2015 to 2025, peak 199 199 0 2015: 1 paper 2015 2016: 0 papers 2016 2017: 0 papers 2017 2018: 0 papers 2018 2019: 2 papers 2019 2020: 31 papers 2020 2021: 108 papers 2021 2022: 164 papers 2022 2023: 199 papers 2023 2024: 152 papers 2024 2025: 51 papers 2025
Papers per year the archive tags with this method, by the paper's archive date (708 dated). Bars are counts, not a trend claim.

Components: the archive holds no method-to-method composition, so PwC's Components table cannot be rebuilt; the Papers list carries no Results column for the same reason (the archive does not join its leaderboard rows to method tags).

Categories archive 2025-07-28

Autoencoding TransformersSequence To Sequence ModelsTransformers

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections