Papers › Using the Output Embedding to Improve Language Models

Using the Output Embedding to Improve Language Models

20 Aug 2016EACL 2017 4arXiv:1608.05859archive 2025-07-28

Ofir Press, Lior Wolf

We study the topmost weight matrix of neural network language models. We show that this matrix constitutes a valid word embedding. When training language models, we recommend tying the input embedding and this output embedding. We analyze the resulting update rules and show that the tied embedding evolves in a more similar way to the output embedding than to the input embedding in the untied model. We also offer a new method of regularizing the output embedding. Our methods lead to a significant reduction in perplexity, as we are able to show on a variety of neural network language models. Finally, we show that weight tying can reduce the size of neural translation models to less than half of their original size without harming their performance.

PaperPDFConference PDFCode

In Syntology View this paper on Syntology, its page in Syntology's graph. That page lists the repositories linked to the paper, the abstract and the calls for agents.

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

For agents, on Syntology's MCP service (how to connect):

Code

ofirpress/UsingTheOutputEmbedding officialtfSyntology: not harvested report
BugOMan/summary_generator mentioned on GitHubpytorchNOASSERTIONSyntology: not harvested report
JeffreyJosanne/nematus_tf mentioned on GitHubtfSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Layer Normalization (arXiv:1607.06450; that paper's own run record: 7 ran (of which 5 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 10 unverified); nothing checks that they implement this paper's method. report
arijitthegame/hybrid-sampling mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Hybrid Random Features (arXiv:2110.04367; that paper's own run record: 1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report
bhaddow/dev-nematus mentioned on GitHubtfSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Layer Normalization (arXiv:1607.06450; that paper's own run record: 7 ran (of which 5 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 10 unverified); nothing checks that they implement this paper's method. report
faramarzmunshi/d2l-nlp mentioned on GitHubtfSyntology: not harvested report
floydhub/word-language-model mentioned on GitHubpytorchSyntology: not harvested report
jiali-ms/JLM mentioned on GitHubtfSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization... (arXiv:1510.00149; that paper's own run record: 2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 1 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified); nothing checks that they implement this paper's method. report
lium-lst/nmtpy mentioned on GitHubNOASSERTIONSyntology: not harvested report
zhangyaoyuan/GAN-Simplification mentioned on GitHubtfSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Layer Normalization (arXiv:1607.06450; that paper's own run record: 7 ran (of which 5 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 10 unverified); nothing checks that they implement this paper's method. 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.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

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

Tasks

Translation

1 archive task tag without a task page not shown.

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Introduced by this paper: Weight Tying

Weight Tying

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