Package: sacRebleu 0.1.2

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>.

Authors:Philipp Koch [aut, cre]

sacRebleu_0.1.2.tar.gz
sacRebleu_0.1.2.zip(r-4.7-x86_64)sacRebleu_0.1.2.zip(r-4.7-arm64)sacRebleu_0.1.2.zip(r-4.6-x86_64)sacRebleu_0.1.2.zip(r-4.6-arm64)sacRebleu_0.1.2.zip(r-4.5-x86_64)
sacRebleu_0.1.2.tgz(r-4.6-x86_64)sacRebleu_0.1.2.tgz(r-4.6-arm64)sacRebleu_0.1.2.tgz(r-4.5-x86_64)sacRebleu_0.1.2.tgz(r-4.5-arm64)
sacRebleu_0.1.2.tar.gz(r-4.7-arm64)sacRebleu_0.1.2.tar.gz(r-4.7-x86_64)sacRebleu_0.1.2.tar.gz(r-4.6-arm64)sacRebleu_0.1.2.tar.gz(r-4.6-x86_64)
sacRebleu_0.1.2.tgz(r-4.6-emscripten)
manual.pdf |manual.html✨
DESCRIPTION |NEWS
card.svg |card.png
sacRebleu/json (API)

# Install 'sacRebleu' in R:

install.packages('sacRebleu', repos = c('https://lazerlambda.r-universe.dev', 'https://cloud.r-project.org'))

Bug tracker:https://github.com/lazerlambda/sacrebleu/issues

Uses libs:

c++– GNU Standard C++ Library v3

On CRAN:

cpp

4.48 score 6 stars 4 scripts 209 downloads 6 exports 6 dependencies

Last updated from:66d92e35f0. Checks:13 ERROR, 2 OK. Indexed: yes.

Target	Result	Time
linux-devel-arm64	ERROR	118
linux-devel-x86_64	ERROR	140
source / vignettes	OK	209
linux-release-arm64	ERROR	116
linux-release-x86_64	ERROR	125
macos-release-arm64	ERROR	130
macos-release-x86_64	ERROR	284
macos-oldrel-arm64	ERROR	143
macos-oldrel-x86_64	ERROR	268
windows-devel-arm64	ERROR	331
windows-devel-x86_64	ERROR	128
windows-release-arm64	ERROR	299
windows-release-x86_64	ERROR	129
windows-oldrel-x86_64	ERROR	93
wasm-release	OK	123

Exports:bleu_corpus bleu_corpus_ids bleu_sentence bleu_sentence_ids validate_arguments validate_references

Dependencies:backports checkmate cli R6 Rcpp tok

sacRebleu

BLEU Score | Smoothing | floor | add-k | Example

Rendered fromsacReBLEU.Rmdusingknitr::rmarkdown

Last update: 2024-04-26
Started: 2024-04-09

Citation

Development and contributors

Readme and manuals

Help Manual

Help page	Topics
This function applies tokenization based on the 'tok' library and computes the BLEU score. An already initialized tokenizer can be provided using the `tokenizer` argument or a valid huggingface identifier (string) can be passed. If the identifier is used only, the tokenizer is newly initialized on every call.	bleu_corpus
Computes BLEU score (Papineni et al., 2002).	bleu_corpus_ids
Compute BLEU for a Sentence with Tokenization	bleu_sentence
Computes BLEU-Score (Papineni et al., 2002).	bleu_sentence_ids
Validate Arguments	validate_arguments
Validate References	validate_references