Papers
arxiv:1804.08771

A Call for Clarity in Reporting BLEU Scores

Published on Sep 12, 2018
Authors:

Abstract

BLEU metric variability in machine translation stems from inconsistent parameter reporting and reference processing, prompting adoption of standardized WMT scheme and introduction of SacreBLEU tool.

The field of machine translation faces an under-recognized problem because of inconsistency in the reporting of scores from its dominant metric. Although people refer to "the" BLEU score, BLEU is in fact a parameterized metric whose values can vary wildly with changes to these parameters. These parameters are often not reported or are hard to find, and consequently, BLEU scores between papers cannot be directly compared. I quantify this variation, finding differences as high as 1.8 between commonly used configurations. The main culprit is different tokenization and normalization schemes applied to the reference. Pointing to the success of the parsing community, I suggest machine translation researchers settle upon the BLEU scheme used by the annual Conference on Machine Translation (WMT), which does not allow for user-supplied reference processing, and provide a new tool, SacreBLEU, to facilitate this.

Community

Sign up or log in to comment

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/1804.08771 in a model README.md to link it from this page.

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/1804.08771 in a dataset README.md to link it from this page.

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/1804.08771 in a Space README.md to link it from this page.

Collections including this paper 0

No Collection including this paper

Add this paper to a collection to link it from this page.