Papers › Improving Neural Language Models with a Continuous Cache

Improving Neural Language Models with a Continuous Cache

13 Dec 2016arXiv:1612.04426archive 2025-07-28

Edouard Grave, Armand Joulin, Nicolas Usunier

We propose an extension to neural network language models to adapt their prediction to the recent history. Our model is a simplified version of memory augmented networks, which stores past hidden activations as memory and accesses them through a dot product with the current hidden activation. This mechanism is very efficient and scales to very large memory sizes. We also draw a link between the use of external memory in neural network and cache models used with count based language models. We demonstrate on several language model datasets that our approach performs significantly better than recent memory augmented networks.

PaperPDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

14 repositories listed; official and paper-mentioned ones first.

AtheMathmo/lookahead-lstm mentioned on GitHubpytorchBSD-3-Clause report
SachinIchake/KALM mentioned on GitHubpytorchBSD-3-Clause report
ari-holtzman/genlm mentioned on GitHubpytorchBSD-3-Clause report
arvieFrydenlund/awd-lstm-lm mentioned on GitHubpytorchBSD-3-Clause report
jb33k/awd-lstm-lm-ThinkNet mentioned on GitHubpytorchBSD-3-Clause report
llppff/ptb-lstmorqrnn-pytorch mentioned on GitHubpytorchBSD-3-Clause report
philippwirth/awd-lstm-test mentioned on GitHubpytorchBSD-3-Clause report
philippwirth/treelangrnn mentioned on GitHubpytorchBSD-3-Clause report
salesforce/awd-lstm-lm mentioned on GitHubpytorchBSD-3-Clause report
soyoung97/awd-lstm-gru mentioned on GitHubpytorchBSD-3-Clause report
uclanlp/NamedEntityLanguageModel mentioned on GitHubpytorchBSD-3-Clause report
dmlc/gluon-nlp mxnetApache-2.0 report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Language ModelingLanguage Modelling

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Language Modelling WikiText-103 Neural cache model (size = 2,000) Test perplexity 40.8 #80 of 89 Archive leaderboard report
Language Modelling WikiText-103 Neural cache model (size = 100) Test perplexity 44.8 #81 of 89 Archive leaderboard report
Language Modelling WikiText-103 LSTM Test perplexity 48.7 #85 of 89 Archive leaderboard report
Language Modelling WikiText-2 Grave et al. (2016) - LSTM + continuous cache pointer Test perplexity 68.9 #33 of 38 Archive leaderboard report
Language Modelling WikiText-2 Grave et al. (2016) - LSTM Test perplexity 99.3 #37 of 38 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

Introduced by this paper: Neural Cache

AdaGradDropoutGradient ClippingLSTMNeural CacheSigmoid ActivationTanh Activation

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