Methods › Natural Language Processing › Transformers › RoBERTa

RoBERTa

913 papers tagged archive 2025-07-28

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

RoBERTa is an extension of BERT with changes to the pretraining procedure. The modifications include:

Source: RoBERTa: A Robustly Optimized BERT Pretraining Approach

Papers archive 2025-07-28

30 shown of 913, 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 477 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 Modelling145
Language Modeling128
Sentence103
Sentiment Analysis75
Question Answering68
Text Classification65
text-classification56
Natural Language Understanding45
Classification44
Transfer Learning43
Data Augmentation42
Named Entity Recognition40
named-entity-recognition39
Named Entity Recognition (NER)35
Natural Language Inference33
NER32
Reading Comprehension28
Articles26
Word Embeddings26
Decoder23

Usage over time archive 2025-07-28

Papers per year tagged with RoBERTa: 2019 to 2025, peak 205 205 0 2019: 19 papers 2019 2020: 168 papers 2020 2021: 205 papers 2021 2022: 138 papers 2022 2023: 172 papers 2023 2024: 159 papers 2024 2025: 52 papers 2025
Papers per year the archive tags with this method, by the paper's archive date (913 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

Transformers

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