Methods › General › Attention Mechanisms › Location-based Attention

Location-based Attention

37 papers tagged archive 2025-07-28

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

Location-based Attention is an attention mechanism in which the alignment scores are computed from solely the target hidden state 𝐡ₜ as follows:

𝐚ₜ = softmax(𝐖ₐ𝐡ₜ)

Source: Effective Approaches to Attention-based Neural Machine...

Papers archive 2025-07-28

30 shown of 37, 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 74 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
Question Answering6
Retrieval5
Translation5
Decoder4
Machine Translation4
Language Modeling3
Language Modelling3
Sentence3
Automatic Speech Recognition2
Automatic Speech Recognition (ASR)2
BIG-bench Machine Learning2
Denoising2
Hallucination2
Information Retrieval2
Reading Comprehension2
Segmentation2
Speech Recognition2
Text Generation2
Transfer Learning2
speech-recognition2

Usage over time archive 2025-07-28

Papers per year tagged with Location-based Attention: 2015 to 2025, peak 7 7 0 2015: 2 papers 2015 2016: 4 papers 2016 2017: 3 papers 2017 2018: 7 papers 2018 2019: 7 papers 2019 2020: 1 paper 2020 2021: 1 paper 2021 2022: 1 paper 2022 2023: 4 papers 2023 2024: 5 papers 2024 2025: 2 papers 2025
Papers per year the archive tags with this method, by the paper's archive date (37 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

Attention Mechanisms

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