Methods › Natural Language Processing › Transformers › ETC

Extended Transformer Construction

ETC

36 papers tagged archive 2025-07-28

Introduced by Joshua Ainslie et al. in ETC: Encoding Long and Structured Inputs in Transformers

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

Extended Transformer Construction, or ETC, is an extension of the Transformer architecture with a new attention mechanism that extends the original in two main ways: (1) it allows scaling up the input length from 512 to several thousands; and (2) it can ingesting structured inputs instead of just linear sequences. The key ideas that enable ETC to achieve these are a new global-local attention mechanism, coupled with relative position encodings. ETC also allows lifting weights from existing BERT models, saving computational resources while training.

PaperSource

Papers archive 2025-07-28

30 shown of 36, 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 38 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
Scheduling3
Language Modelling2
Multi-Armed Bandits2
Question Answering2
Reinforcement Learning (RL)2
Thompson Sampling2
reinforcement-learning2
BIG-bench Machine Learning1
Deep Reinforcement Learning1
Diagnostic1
Disease Prediction1
Language Modeling1
Linguistic Acceptability1
Machine Translation1
Management1
Masked Language Modeling1
Model Predictive Control1
Model Selection1
Natural Language Inference1
Natural Questions1

Usage over time archive 2025-07-28

Papers per year tagged with ETC: 2020 to 2025, peak 9 9 0 2020: 5 papers 2020 2021: 9 papers 2021 2022: 8 papers 2022 2023: 6 papers 2023 2024: 5 papers 2024 2025: 3 papers 2025
Papers per year the archive tags with this method, by the paper's archive date (36 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