Methods › Natural Language Processing › Language Models › mT5

mT5

104 papers tagged archive 2025-07-28

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

mt5 is a multilingual variant of T5 that was pre-trained on a new Common Crawl-based dataset covering $101$ languages.

Source: mT5: A massively multilingual pre-trained text-to-text...

Papers archive 2025-07-28

30 shown of 104, 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 133 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
Translation17
Language Modelling16
Machine Translation16
Question Answering14
Language Modeling13
Decoder12
Cross-Lingual Transfer11
Transfer Learning11
Natural Language Understanding9
XLM-R9
Abstractive Text Summarization8
Sentence8
Diversity7
Denoising5
Natural Language Inference5
Text Generation5
Text Summarization5
Articles4
Masked Language Modeling4
Multilingual NLP4

Usage over time archive 2025-07-28

Papers per year tagged with mT5: 2020 to 2025, peak 34 34 0 2020: 2 papers 2020 2021: 12 papers 2021 2022: 34 papers 2022 2023: 21 papers 2023 2024: 30 papers 2024 2025: 5 papers 2025
Papers per year the archive tags with this method, by the paper's archive date (104 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

Language Models

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