sacRebleu: Metrics for Assessing the Quality of Generated Text

Implementation of the BLEU-Score in 'C++' to evaluate the quality of generated text. The BLEU-Score, introduced by Papineni et al. (2002) <doi:10.3115/1073083.1073135>, is a metric for evaluating the quality of generated text. It is based on the n-gram overlap between the generated text and reference texts. Additionally, the package provides some smoothing methods as described in Chen and Cherry (2014) <doi:10.3115/v1/W14-3346>.

Version: 0.1.3
Depends: R (≥ 4.2.0)
Imports: checkmate, Rcpp (≥ 1.0.12), tok
LinkingTo: Rcpp
Suggests: knitr, rmarkdown, hfhub, testthat (≥ 3.0.0), withr
Published: 2024-04-30
Author: Philipp Koch [aut, cre]
Maintainer: Philipp Koch <PhillKoch at>
License: GPL-2 | GPL-3 [expanded from: GPL (≥ 2)]
NeedsCompilation: yes
SystemRequirements: Rust tool chain w/ cargo, libclang/llvm-config
Language: en-US
Materials: README NEWS
CRAN checks: sacRebleu results


Reference manual: sacRebleu.pdf
Vignettes: sacRebleu


Package source: sacRebleu_0.1.3.tar.gz
Windows binaries: r-devel:, r-release:, r-oldrel:
macOS binaries: r-release (arm64): sacRebleu_0.1.3.tgz, r-oldrel (arm64): sacRebleu_0.1.3.tgz, r-release (x86_64): sacRebleu_0.1.3.tgz, r-oldrel (x86_64): sacRebleu_0.1.3.tgz


Please use the canonical form to link to this page.