BLEU might be Guilty but References are not Innocent
Open accessThe DOI matches its Crossref record; 6 of the 6 references it cites were found in a registry or an index.
Abstract
The quality of automatic metrics for machine translation has been increasingly called into question, especially for high-quality systems.This paper demonstrates that, while choice of metric is important, the nature of the references is also critical.We study different methods to collect references and compare their value in automated evaluation by reporting correlation with human evaluation for a variety of systems and metrics.Motivated by the finding that typical references exhibit poor diversity, concentrating around translationese language, we develop a paraphrasing task for linguists to perform on existing reference translations, which counteracts this bias.Our method yields higher correlation with human judgment not only for the submissions of WMT 2019 English→German, but also for Back-translation and APE augmented MT output, which have been shown to have low correlation with automatic metrics using standard references.We demonstrate that our methodology improves correlation with all modern evaluation metrics we look at, including embedding-based methods.To complete this picture, we reveal that multireference BLEU does not improve the correlation for high quality output, and present an alternative multi-reference formulation that is more effective.
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.
Integrity signals
Registry
Cites
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.
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
BERTScore: Evaluating Text Generation with BERT
Zhang, T., Kishore, V., Wu, F., Weinberger, K. Q., & Artzi, Y. (2019) · arXiv · doi:10.48550/arxiv.1904.09675 · Cited by 2,865
A Call for Clarity in Reporting BLEU Scores
Post, M. (2018) · Proceedings of the Third Conference on Machine Translation: Research Papers · doi:10.18653/v1/w18-6319 · Cited by 2,112
A Call for Clarity in Reporting BLEU Scores
Post, M. (2018) · arXiv · doi:10.48550/arxiv.1804.08771 · Cited by 2,111
chrF: character n-gram F-score for automatic MT evaluation
Popović, M. (2015) · Proceedings of the Tenth Workshop on Statistical Machine Translation · doi:10.18653/v1/w15-3049 · Cited by 1,220
Findings of the 2016 Conference on Machine Translation
Bojar, O., Chatterjee, R., Federmann, C., Graham, Y., Haddow, B., Huck, M., Jimeno Yepes, A., Koehn, P., Logacheva, V., Monz, C., et al. (2016) · Proceedings of the First Conference on Machine Translation: Volume 2, Shared Task Papers · doi:10.18653/v1/w16-2301 · Cited by 539
Automatic Machine Translation Evaluation in Many Languages via Zero-Shot Paraphrasing
Thompson, B., & Post, M. (2020) · Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2020.emnlp-main.8 · Cited by 128
Cited by
Benchmarking Large Language Models for News Summarization
Zhang, T., Ladhak, F., Durmus, E., Liang, P., McKeown, K., & Hashimoto, T. B. (2024) · Transactions of the Association for Computational Linguistics · doi:10.1162/tacl_a_00632 · Cited by 415
Benchmarking Large Language Models for News Summarization
Zhang, T., Ladhak, F., Durmus, E., Liang, P., McKeown, K., & Hashimoto, T. B. (2023) · arXiv · doi:10.48550/arxiv.2301.13848 · Cited by 415
Experts, Errors, and Context: A Large-Scale Study of Human Evaluation for Machine Translation
Freitag, M., Foster, G., Grangier, D., Ratnakar, V., Tan, Q., & Macherey, W. (2021) · Transactions of the Association for Computational Linguistics · doi:10.1162/tacl_a_00437 · Cited by 271
Self-citationReformulating Unsupervised Style Transfer as Paraphrase Generation
Krishna, K., Wieting, J., & Iyyer, M. (2020) · Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2020.emnlp-main.55 · Cited by 185
The GEM Benchmark: Natural Language Generation, its Evaluation and Metrics
Gehrmann, S., Adewumi, T., Aggarwal, K., Ammanamanchi, P. S., Aremu, A., Bosselut, A., Chandu, K. R., Clinciu, M.-A., Das, D., Dhole, K., et al. (2021) · Proceedings of the 1st Workshop on Natural Language Generation, Evaluation, and Metrics (GEM 2021) · doi:10.18653/v1/2021.gem-1.10 · Cited by 159
Metadata
- Authors
- Freitag, M., Grangier, D., & Caswell, I.
- Venue
- Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)
- Published
- 2020
- Pages
- 61-71
- OpenAlex
- W3016234399
- Cited by
- 106
- References
- 6
- FWCI
- 8.47
- 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: BLEU might be Guilty but References are not Innocent. https://app.cochat.ai/papers/10.18653/v1/2020.emnlp-main.5
- The paper
- Freitag, M., Grangier, D., & Caswell, I. (2020). BLEU might be Guilty but References are not Innocent. Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP). https://doi.org/10.18653/v1/2020.emnlp-main.5
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.