CoChat

Fixed Encoder Self-Attention Patterns in Transformer-Based Machine Translation

Open access
Raganato, Alessandro, Scherrer, Yves, Tiedemann, Jörg · 2020 · Findings of the Association for Computational Linguistics: EMNLP 2020
Cited by 86

The DOI matches its Crossref record; 21 of the 21 references it cites were found in a registry or an index.

Abstract

Transformer-based models have brought a radical change to neural machine translation.A key feature of the Transformer architecture is the so-called multi-head attention mechanism, which allows the model to focus simultaneously on different parts of the input.However, recent works have shown that most attention heads learn simple, and often redundant, positional patterns.In this paper, we propose to replace all but one attention head of each encoder layer with simple fixed -non-learnable -attentive patterns that are solely based on position and do not require any external knowledge.Our experiments with different data sizes and multiple language pairs show that fixing the attention heads on the encoder side of the Transformer at training time does not impact the translation quality and even increases BLEU scores by up to 3 points in low-resource scenarios.

Overview

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

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

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

Integrity signals

Registry

Crossref · 10.18653/v1/2020.findings-emnlp.49

Cites

21 of 21 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.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

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 21 references

Cited by

See all 86

Metadata

Authors
Raganato, A., Scherrer, Y., & Tiedemann, J.
Venue
Findings of the Association for Computational Linguistics: EMNLP 2020
Published
2020
Pages
556-568
OpenAlex
W3006801027
Cited by
86
References
21
FWCI
7.06
Type
conference paper
Language
en
Open access
gold

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: Fixed Encoder Self-Attention Patterns in Transformer-Based Machine Translation. https://app.cochat.ai/papers/10.18653/v1/2020.findings-emnlp.49
The paper
Raganato, A., Scherrer, Y., & Tiedemann, J. (2020). Fixed Encoder Self-Attention Patterns in Transformer-Based Machine Translation. Findings of the Association for Computational Linguistics: EMNLP 2020. https://doi.org/10.18653/v1/2020.findings-emnlp.49

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.