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

The DOI matches its Crossref record; 39 of the 39 references it cites were found in a registry or an index.

QuickEdit: Editing Text and Translations by Crossing Words Out

Open access
Grangier, David, Auli, Michael · 2018 · Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers)

Abstract

David Grangier, Michael Auli. Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers). 2018.

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/n18-1025

Cites

39 of 39 references verified0 citation errors · 0 not checkable

Statistics

Figures

Figure 1 QuickEdit architecture for translation post-editing. The decoder attends to both encodings, one for the source and one for the initial translation (guess) with deletion markers (X on the diagram). Our simplified schema shows one convolutional block and single-hop attention for readability.
Figure 1 QuickEdit architecture for translation post-editing. The decoder attends to both encodings, one for the source and one for the initial translation (guess) with deletion markers (X on the diagram). Our simplified schema shows one convolutional block and single-hop attention for readability.CC-BY · From the PDF
Figure 2 Post-editing results as a function of the average number of marked tokens per sentence on WMT'14 de-en validation set (45k sentences). QE25, QE50, QE100 refer to QuickEdit models trained with data where respectively 25 , 50 or 100% of the guess tokens not present in the reference were marked to be changed.
Figure 2 Post-editing results as a function of the average number of marked tokens per sentence on WMT'14 de-en validation set (45k sentences). QE25, QE50, QE100 refer to QuickEdit models trained with data where respectively 25 , 50 or 100% of the guess tokens not present in the reference were marked to be changed.CC-BY · From the PDF

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

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

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 39 references

Research works printed but not linked: 5

  1. [8]8. Mauro Cettolo, Jan Niehues, Sebastian Stüker, Luisa Bentivogli, and Marcello Federico. 2014. Report on the 11th IWSLT evaluation campaign. In Proceed- ings of the International Workshop on Spoken Lan- guage Translation, Hanoi, Vietnam.
  2. [17]17. Edgar T. Irons and Frans M. Djorup. 1972. A crt edit- ing system. Communications of the ACM 15(1):16- 20.
  3. [22]22. Jindřich Libovickỳ and Jindřich Helcl. 2017. Attention strategies for multi-source sequence-to-sequence learning. arXiv preprint arXiv:1704.06567 . · arXiv
  4. [33]33. Rico Sennrich, Barry Haddow, and Alexandra Birch. 2016a. Edinburgh Neural Machine Translation Sys- tems for WMT 16. In Proc. of WMT.
  5. [34]34. Rico Sennrich, Barry Haddow, and Alexandra Birch. 2016b. Neural Machine Translation of Rare Words with Subword Units. In Proc. of ACL.

Cited by

See all 21

Metadata

Authors
Grangier, D., & Auli, M.
Affiliations
Meta (United States) (US)
Venue
Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers)
Published
2018
Pages
272-282
OpenAlex
W2796032388
Cited by
20
References
39
Citations by year
2024: 1 · 2022: 6 · 2021: 4 · 2020: 5 · 2019: 4
FWCI
1.33
Type
conference paper
Language
en
Open access
Licence
cc-by
Locations
Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT) (publishedVersion, cc-by)
Topics
  • Physical Sciences › Computer Science › Artificial Intelligence › Natural Language Processing Techniques
  • Physical Sciences › Computer Science › Artificial Intelligence › Topic Modeling
  • Social Sciences › Arts and Humanities › Language and Linguistics › Lexicography and Language Studies
Keywords
text editing, word deletion, human-in-the-loop, translation quality assessment

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: QuickEdit: Editing Text and Translations by Crossing Words Out. https://app.cochat.ai/papers/10.18653/v1/n18-1025
The paper
Grangier, D., & Auli, M. (2018). QuickEdit: Editing Text and Translations by Crossing Words Out. Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers). https://doi.org/10.18653/v1/n18-1025

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.