Student or educator? Sign up with your school email and get 6 months of Pro free.
Cited by 596

The DOI matches its Crossref record; 43 of the 43 references it cites were found in a registry or an index.

Using the Output Embedding to Improve Language Models

Open access
Press, Ofir, Wolf, Lior · 2017 · Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 2, Short Papers

Abstract

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.

Overview

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.18653/v1/e17-2025

Cites

43 of 43 references verified0 citation errors · 0 not checkable

Statistics

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

Cites

Show all 43 references

Cited by

See all 596

Metadata

Authors
Press, O., & Wolf, L.
Venue
Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 2, Short Papers
Published
2017
Pages
157-163
OpenAlex
W2514713644
Cited by
596
References
43
FWCI
48.65
Type
conference paper
Language
en
Open access
hybrid

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

How to cite

Cite CoChat for the checks on this page, and the paper for its own findings.

This page
CoChat. (2026). Citation check: Using the Output Embedding to Improve Language Models. https://app.cochat.ai/papers/10.18653/v1/e17-2025
The paper
Press, O., & Wolf, L. (2017). Using the Output Embedding to Improve Language Models. Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 2, Short Papers. https://doi.org/10.18653/v1/e17-2025

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.