ruimtehol: Learn Text 'Embeddings' with 'Starspace'
Wraps the 'StarSpace' library <https://github.com/facebookresearch/StarSpace>
allowing users to calculate word, sentence, article, document, webpage, link and entity 'embeddings'.
By using the 'embeddings', you can perform text based multi-label classification,
find similarities between texts and categories, do collaborative-filtering based recommendation
as well as content-based recommendation, find out relations between entities, calculate
graph 'embeddings' as well as perform semi-supervised learning and multi-task learning on plain text.
The techniques are explained in detail in the paper: 'StarSpace: Embed All The Things!' by Wu et al. (2017), available at <arXiv:1709.03856>.
| Version: |
0.3 |
| Depends: |
R (≥ 2.10) |
| Imports: |
Rcpp (≥ 0.11.5), utils, graphics, stats |
| LinkingTo: |
Rcpp, BH |
| Suggests: |
udpipe, data.table |
| Published: |
2020-11-29 |
| Author: |
Jan Wijffels [aut, cre, cph] (R wrapper),
BNOSAC [cph] (R wrapper),
Facebook, Inc. [cph] (Starspace (BSD licensed)) |
| Maintainer: |
Jan Wijffels <jwijffels at bnosac.be> |
| License: |
MPL-2.0 |
| URL: |
https://github.com/bnosac/ruimtehol |
| NeedsCompilation: |
yes |
| SystemRequirements: |
C++11 |
| Materials: |
README NEWS |
| In views: |
NaturalLanguageProcessing |
| CRAN checks: |
ruimtehol results |
Documentation:
Downloads:
Linking:
Please use the canonical form
https://CRAN.R-project.org/package=ruimtehol
to link to this page.