Papers › Pointer Sentinel Mixture Models

Pointer Sentinel Mixture Models

26 Sep 2016arXiv:1609.07843archive 2025-07-28

Stephen Merity, Caiming Xiong, James Bradbury, Richard Socher

Recent neural network sequence models with softmax classifiers have achieved their best language modeling performance only with very large hidden states and large vocabularies. Even then they struggle to predict rare or unseen words even if the context makes the prediction unambiguous. We introduce the pointer sentinel mixture architecture for neural sequence models which has the ability to either reproduce a word from the recent context or produce a word from a standard softmax classifier. Our pointer sentinel-LSTM model achieves state of the art language modeling performance on the Penn Treebank (70.9 perplexity) while using far fewer parameters than a standard softmax LSTM. In order to evaluate how well language models can exploit longer contexts and deal with more realistic vocabularies and larger corpora we also introduce the freely available WikiText corpus.

PaperPDFCodeCode Syntology ran

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

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="1609.07843")

Code

Syntology Ran 2 of 9 code samples harvested from 3 repositories linked to this paper; 7 have no recorded run. Of those that ran: 1 ran · fixture could not drive it; 1 ran with no contract checked.

By repository: community (archive-listed): 9 samples from 3 repositories, 2 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

axiomlab/Cable mentioned on GitHubpytorch report
elanmart/psmm mentioned on GitHubpytorch report
emanjavacas/pie mentioned on GitHubpytorch report
jfisher52/influence_theory mentioned on GitHubpytorch report
kafura-kafiri/tf2-elmo mentioned on GitHubtf report
kkirchheim/pytorch-ood mentioned on GitHubpytorchApache-2.0 report
mikekestemont/pie mentioned on GitHubpytorchMIT report
pasta41/deception mentioned on GitHubpytorch report
yangrui123/Hidden mentioned on GitHubtf report
zhongping-zhang/engine mentioned on GitHubpytorchMIT 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

9 samples harvested; 2 ran; 0 honoured the contract we drafted; 7 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

1ran · fixture could not drive it
1ran
7unverified

Licence: 1 of the 9 samples is pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from 3 repositories linked to this paper, official or community; each sample names its own and says which. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples from a repository marked official are listed first. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of four reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

DotScorer emanjavacas/pie/pie/models/decoder.py community (archive-listed) ran · fixture could not drive it fingerprinted MIT (permissive) · 0414551c62a09f12 · report
PointerSentinel elanmart/psmm/psmm/model.py community (archive-listed) ran no licence file found · pointer only · f9fe5f4ff2349a26 · report
Attention emanjavacas/pie/pie/models/decoder.py community (archive-listed) unverified MIT (permissive) · 48e865d17f832cf9 · report
AttentionalDecoder emanjavacas/pie/pie/models/decoder.py community (archive-listed) unverified MIT (permissive) · a23814ddbf05037d · report
BahdanauScorer emanjavacas/pie/pie/models/decoder.py community (archive-listed) unverified MIT (permissive) · 99b391f7c6bb9f4c · report
Beam emanjavacas/pie/pie/models/decoder.py community (archive-listed) unverified MIT (permissive) · 53b424349970dcd4 · report
GeneralScorer emanjavacas/pie/pie/models/decoder.py community (archive-listed) unverified MIT (permissive) · 94e662f236fb57ff · report
get_known_and_ambigous_tokens mikekestemont/pie/pie/models/scorer.py community (archive-listed) unverified MIT (permissive) · 4ee2cb07bb0ad310 · report
get_pretrained_embeddings mikekestemont/pie/pie/models/loaders.py community (archive-listed) unverified MIT (permissive) · 68f526c834cab2f3 · report

Tasks

Language ModelingLanguage Modelling

Datasets

Introduced by this paper, per the archive.

WikiText-103WikiText-2

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Introduced by this paper: Pointer Sentinel-LSTM

LSTMPointer NetworkPointer Sentinel-LSTMSigmoid ActivationSoftmaxTanh ActivationVariational DropoutZoneout

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