Learning text representations and text classifiers may rely on the same simple and efficient approach. 'fastText' is an open-source, free, lightweight library that allows users to perform both tasks. It transforms text into continuous vectors that can later be used on many language related task. It works on standard, generic hardware (no 'GPU' required). It also includes model size reduction feature. 'fastText' original source code is available at <https://github.com/facebookresearch/fastText>.
Version: | 0.2.5 |
Depends: | R (≥ 3.3) |
Imports: | methods, Rcpp (≥ 0.12.12), assertthat |
LinkingTo: | Rcpp |
Suggests: | knitr, testthat |
Published: | 2018-01-04 |
Author: | Michaël Benesty [aut, cre, cph], Facebook, Inc [cph] |
Maintainer: | Michaël Benesty <michael at benesty.fr> |
BugReports: | https://github.com/pommedeterresautee/fastrtext/issues |
License: | MIT + file LICENSE |
URL: | https://github.com/pommedeterresautee/fastrtext, https://pommedeterresautee.github.io/fastrtext/ |
NeedsCompilation: | yes |
Materials: | NEWS |
CRAN checks: | fastrtext results |
Reference manual: | fastrtext.pdf |
Vignettes: |
List of commands Supervised learning Unsupervised learning |
Package source: | fastrtext_0.2.5.tar.gz |
Windows binaries: | r-devel: fastrtext_0.2.5.zip, r-release: fastrtext_0.2.5.zip, r-oldrel: fastrtext_0.2.5.zip |
OS X El Capitan binaries: | r-release: fastrtext_0.2.5.tgz |
OS X Mavericks binaries: | r-oldrel: fastrtext_0.2.5.tgz |
Old sources: | fastrtext archive |
Reverse suggests: | projector |
Please use the canonical form https://CRAN.R-project.org/package=fastrtext to link to this page.