fastText: Efficient Learning of Word Representations and Sentence Classification

An interface to the 'fastText' <> library for efficient learning of word representations and sentence classification. The 'fastText' algorithm is explained in detail in (i) "Enriching Word Vectors with subword Information", Piotr Bojanowski, Edouard Grave, Armand Joulin, Tomas Mikolov, 2017, <doi:10.1162/tacl_a_00051>; (ii) "Bag of Tricks for Efficient Text Classification", Armand Joulin, Edouard Grave, Piotr Bojanowski, Tomas Mikolov, 2017, <doi:10.18653/v1/e17-2068>; (iii) " Compressing text classification models", Armand Joulin, Edouard Grave, Piotr Bojanowski, Matthijs Douze, Herve Jegou, Tomas Mikolov, 2016, <doi:10.48550/arXiv.1612.03651>.

Version: 1.0.4
Depends: R (≥ 3.2.3)
Imports: Rcpp (≥ 1.0.0), ggplot2, grid, utils, glue, data.table, stats
LinkingTo: Rcpp
Suggests: testthat, covr, knitr, rmarkdown
Published: 2024-02-17
DOI: 10.32614/CRAN.package.fastText
Author: Lampros Mouselimis ORCID iD [aut, cre], Facebook Inc [cph]
Maintainer: Lampros Mouselimis <mouselimislampros at>
License: MIT + file LICENSE
NeedsCompilation: yes
SystemRequirements: Generally, fastText builds on modern Mac OS and Linux distributions. Since it uses some C++11 features, it requires a compiler with good C++11 support. These include a (g++-4.7.2 or newer) or a (clang-3.3 or newer).
Citation: fastText citation info
Materials: README NEWS
CRAN checks: fastText results


Reference manual: fastText.pdf
Vignettes: Language Identification using the 'fastText' package (a Benchmark)
Functionality of the fastText R package


Package source: fastText_1.0.4.tar.gz
Windows binaries: r-devel:, r-release:, r-oldrel:
macOS binaries: r-release (arm64): fastText_1.0.4.tgz, r-oldrel (arm64): fastText_1.0.4.tgz, r-release (x86_64): fastText_1.0.4.tgz, r-oldrel (x86_64): fastText_1.0.4.tgz
Old sources: fastText archive


Please use the canonical form to link to this page.