fastText

fastText is a library for learning of word embeddings and text classification created by Facebook's AI Research (FAIR) lab[3][4][5][6]. The model allows one to create an unsupervised learning or supervised learning algorithm for obtaining vector representations for words. Facebook makes available pretrained models for 294 languages.[7] fastText uses a neural network for word embedding.

fastText
Developer(s)Facebook's AI Research (FAIR) lab[1]
Initial releaseNovember 9, 2015 (2015-11-09)
Stable release
0.2.0[2] / December 19, 2018 (2018-12-19)
Repositorygithub.com/facebookresearch/fastText
Written inC++, Python
PlatformLinux, macOS, Windows
TypeMachine learning library
LicenseBSD License
Websitefasttext.cc

Algorithm of fasttext is based on these two papers:[8]

See also

References

  1. Mannes, John. "Facebook's fastText library is now optimized for mobile". TechCrunch. Retrieved 12 January 2018.
  2. Onur Çelebi (2018-12-19). "facebookresearch/fastText/releases/tag/v0.2.0". Facebook. Retrieved 2019-03-18.
  3. Mannes, John. "Facebook's fastText library is now optimized for mobile". TechCrunch. Retrieved 12 January 2018.
  4. Ryan, Kevin J. "Facebook's New Open Source Software Can Learn 1 Billion Words in 10 Minutes". Inc. Retrieved 12 January 2018.
  5. Low, Cherlynn. "Facebook is open-sourcing its AI bot-building research". Engadget. Retrieved 12 January 2018.
  6. Mannes, John. "Facebook's Artificial Intelligence Research lab releases open source fastText on GitHub". TechCrunch. Retrieved 12 January 2018.
  7. Sabin, Dyani. "Facebook Makes A.I. Program Available in 294 Languages". Inverse. Retrieved 12 January 2018.
  8. "FastText". Facebook Research. Retrieved 2019-12-16.
This article is issued from Wikipedia. The text is licensed under Creative Commons - Attribution - Sharealike. Additional terms may apply for the media files.