Methods › Natural Language Processing › Language Model Components › Neural Cache

Neural Cache

4 papers tagged archive 2025-07-28

Introduced by Edouard Grave et al. in Improving Neural Language Models with a Continuous Cache

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

A Neural Cache, or a Continuous Cache, is a module for language modelling which stores previous hidden states in memory cells. They are then used as keys to retrieve their corresponding word, that is the next word. There is no transformation applied to the storage during writing and reading.

More formally it exploits the hidden representations hₜ to define a probability distribution over the words in the cache. As illustrated in the Figure, the cache stores pairs (hᵢ, xᵢ₊₁) of a hidden representation, and the word which was generated based on this representation (the vector hᵢ encodes the history xᵢ, …, x₁). At time t, we then define a probability distribution over words stored in the cache based on the stored hidden representations and the current one hₜ as:

p_(cache)(w | h_(1…t), x_(1…t)) ∝∑ᵗ⁻¹ᵢ₌₁1_(set(w=xᵢ₊₁)) exp(θₕ>hₜᵀhᵢ)

where the scalar θ is a parameter which controls the flatness of the distribution. When θ is equal to zero, the probability distribution over the history is uniform, and the model is equivalent to a unigram cache model.

PaperSource

In Syntology about another paper, arXiv:1805.03718: the paper matched by title held, no code (no_code; paper_only). The lookup matched a paper by its title, arXiv:1805.03718, not a method entry. About another paper: this answer is about arXiv:1805.03718, while the archive credits arXiv:1612.04426, so it does not say whether this method has code.

Origin paper of this answer, arXiv:1805.03718 (its page on Syntology).

Syntology's have check for this name (free, it answers coverage only), read 2026-10-05; ask it again live. A level is the served verification level of that one answer; nothing here is summed across methods.

Papers archive 2025-07-28

archive papers tagged: 4 · with a code link: 2 · where Syntology ran a sample: 1 (1 with a run with no instrument failure, 0 where every run was a failure of Syntology's instrument) Syntology

Show: all tagged papersonly where code ran (1 of 4 tagged: 1 with a run with no instrument failure, 0 where every run was a failure of Syntology's instrument)

Page 1 of 1: papers 1 to 4 of 4, newest first by the archive's date (ties by slug), in archive order.

Repository counts are the archive's code-links table. A Syntology line states what Syntology ran from that paper's harvested code, as “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the instrument figure counts failures of Syntology's instrument, not of the code. It is per sample and not a correctness claim. When the archive marks a repository official for the paper, the line starts with that repository's state (the archive's flag, not a verdict on who wrote the code; “community repositories only” when every sample that ran came from a community repository, “official: no sample here; runs from other or unrecorded repositories” when some came from a repository the paper names or has in its text, or from none recorded); hover it for the repositories the samples that ran came from.

Tasks archive 2025-07-28

7 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 Modeling2
Language Modelling2
CPU1
GPU1
Image Classification1
Quantization1
Translation1

Usage over time archive 2025-07-28

Papers per year tagged with Neural Cache: 2016 to 2018, peak 2 2 0 2016: 1 paper 2016 2017: 1 paper 2017 2018: 2 papers 2018
Papers per year the archive tags with this method, by the paper's archive date (4 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 Model Components

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