[go: nahoru, domu]
Jump to content

FastText: Difference between revisions

From Wikipedia, the free encyclopedia
Browse history interactively
← Previous edit
Content deleted Content added
VisualWikitext
Gweorth (talk | contribs)
258 edits
 
(31 intermediate revisions by 22 users not shown)
Line 1: Line 1:
{{lowercase title}}
{{lowercase title}}
{{Infobox software

| name = fastText
⚫
'''fastText''' is a library for learning of [[word embedding]]s and sentence classification created by [[Facebook]]'s AI Research (FAIR) lab<ref>{{cite web|last1=Mannes|first1=John|title=Facebook’s fastText library is now optimized for mobile|url=https://techcrunch.com/2017/05/02/facebooks-fasttext-library-is-now-optimized-for-mobile/|website=[[TechCrunch]]|accessdate=12 January 2018}}</ref><ref>{{cite web|last1=Ryan|first1=Kevin J.|title=Facebook's New Open Source Software Can Learn 1 Billion Words in 10 Minutes|url=https://www.inc.com/kevin-j-ryan/facebook-open-source-fasttext-learns-1-billion-words-in-10-minutes.html|website=[[Inc. (magazine)|Inc.]]|accessdate=12 January 2018}}</ref><ref>{{cite web|last1=Low|first1=Cherlynn|title=Facebook is open-sourcing its AI bot-building research|url=https://www.engadget.com/2016/08/18/facebook-open-sourcing-fasttext/|website=[[Engadget]]|accessdate=12 January 2018}}</ref><ref>{{cite web|last1=Mannes|first1=John|title=Facebook’s Artificial Intelligence Research lab releases open source fastText on GitHub|url=https://techcrunch.com/2016/08/18/facebooks-artificial-intelligence-research-lab-releases-open-source-fasttext-on-github/|website=[[TechCrunch]]|accessdate=12 January 2018}}</ref>. The model is an [[unsupervised learning]] algorithm for obtaining vector representations for words. Facebook makes available pretrained models for 294 languages.<ref>{{cite web|last1=Sabin|first1=Dyani|title=Facebook Makes A.I. Program Available in 294 Languages|url=https://www.inverse.com/article/31075-facebook-machine-learning-language-fasttext|website=[[Inverse (website)|Inverse]]|accessdate=12 January 2018}}</ref>
| logo = FastText.png

| author =

| developer = [[Facebook]]'s AI Research (FAIR) lab<ref>{{cite web|last1=Mannes|first1=John|title=Facebook's fastText library is now optimized for mobile|url=https://techcrunch.com/2017/05/02/facebooks-fasttext-library-is-now-optimized-for-mobile/|website=[[TechCrunch]]|accessdate=12 January 2018}}</ref>
| released = {{Start date and age|2015|11|09}}
| latest release version = 0.9.2<ref name="gith_face_v0.9.2">{{Cite web | title = facebookresearch/fastText/releases/tag/v0.9.2 | author = Onur Çelebi | work = Facebook | date = 2020-04-28 | accessdate = 2020-11-21 | url = https://github.com/facebookresearch/fastText/releases/tag/v0.9.2 | quote = }}</ref>
| latest release date = {{Start date and age|2020|04|28}}
| repo = {{URL|https://github.com/facebookresearch/fastText}}
| programming language = [[C++]], [[Python (programming language)|Python]]
| platform = [[Linux]], [[macOS]], [[Windows]]
| genre = [[Machine learning]] [[Library (computing)|library]]
| license = [[MIT License]]
| website = {{URL|https://fasttext.cc/}}
}}
⚫
'''fastText''' is a library for learning of [[word embedding]]s and text classification created by [[Facebook]]'s AI Research (FAIR) lab.<ref>{{cite web|last1=Mannes|first1=John|title=Facebook's fastText library is now optimized for mobile|url=https://techcrunch.com/2017/05/02/facebooks-fasttext-library-is-now-optimized-for-mobile/|website=[[TechCrunch]]|accessdate=12 January 2018}}</ref><ref>{{cite web|last1=Ryan|first1=Kevin J.|title=Facebook's New Open Source Software Can Learn 1 Billion Words in 10 Minutes|url=https://www.inc.com/kevin-j-ryan/facebook-open-source-fasttext-learns-1-billion-words-in-10-minutes.html|website=[[Inc. (magazine)|Inc.]]|accessdate=12 January 2018}}</ref><ref>{{cite web|last1=Low|first1=Cherlynn|title=Facebook is open-sourcing its AI bot-building research|url=https://www.engadget.com/2016/08/18/facebook-open-sourcing-fasttext/|website=[[Engadget]]|accessdate=12 January 2018}}</ref><ref>{{cite web|last1=Mannes|first1=John|title=Facebook's Artificial Intelligence Research lab releases open source fastText on GitHub|url=https://techcrunch.com/2016/08/18/facebooks-artificial-intelligence-research-lab-releases-open-source-fasttext-on-github/|website=[[TechCrunch]]|accessdate=12 January 2018}}</ref> 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.<ref>{{cite web|last1=Sabin|first1=Dyani|title=Facebook Makes A.I. Program Available in 294 Languages|url=https://www.inverse.com/article/31075-facebook-machine-learning-language-fasttext|website=[[Inverse (website)|Inverse]]|accessdate=12 January 2018}}</ref><ref>{{cite web|title=Wiki word vectors|url=https://fasttext.cc/docs/en/pretrained-vectors.html|website=fastText|language=en-US|accessdate=26 November 2020}}</ref> Several papers describe the techniques used by fastText.<ref>{{Cite web|title=References · fastText|url=https://fasttext.cc/index.html|access-date=2021-09-08|website=fasttext.cc|language=en}}</ref><ref>{{cite arXiv|last1=Bojanowski|first1=Piotr|last2=Grave|first2=Edouard|last3=Joulin|first3=Armand|last4=Mikolov|first4=Tomas|date=2017-06-19|title=Enriching Word Vectors with Subword Information|class=cs.CL|eprint=1607.04606}}</ref><ref>{{cite arXiv|last1=Joulin|first1=Armand|last2=Grave|first2=Edouard|last3=Bojanowski|first3=Piotr|last4=Mikolov|first4=Tomas|date=2016-08-09|title=Bag of Tricks for Efficient Text Classification|class=cs.CL|eprint=1607.01759}}</ref><ref>{{cite arXiv|last1=Joulin|first1=Armand|last2=Grave|first2=Edouard|last3=Bojanowski|first3=Piotr|last4=Douze|first4=Matthijs|last5=Jégou|first5=Hérve|last6=Mikolov|first6=Tomas|date=2016-12-12|title=FastText.zip: Compressing text classification models|class=cs.CL|eprint=1612.03651}}</ref>


== See also ==
== See also ==
* [[Word2vec]]
* [[Word2vec]]
* [[GloVe|GloVe (machine learning)]]
* [[GloVe]]
*[[Artificial neural network|Neural Network]]
*[[Natural language processing|Natural Language Processing]]


==References==
== References ==
{{reflist}}
{{reflist}}


==External links==
== External links ==
* [https://fasttext.cc fastText]
* [https://fasttext.cc fastText]
*https://research.fb.com/downloads/fasttext/
{{asbox|image = Crystal Clear action run.png|subject = technology-related|category = Technology stubs|tempsort = *|name = Template:Tech-stub}}

{{Natural Language Processing}}


[[Category:Natural language processing software]]
[[Category:Natural language processing software]]
[[Category:Software using the MIT license]]

{{free-software-stub}}

Latest revision as of 14:52, 10 January 2024

fastText
Developer(s)Facebook's AI Research (FAIR) lab[1]
Initial releaseNovember 9, 2015; 8 years ago (2015-11-09)
Stable release
0.9.2[2] / April 28, 2020; 4 years ago (2020-04-28)
Repositorygithub.com/facebookresearch/fastText
Written inC++, Python
PlatformLinux, macOS, Windows
TypeMachine learning library
LicenseMIT License
Websitefasttext.cc

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][8] Several papers describe the techniques used by fastText.[9][10][11][12]

See also

[edit]

References

[edit]
  1. ^ Mannes, John. "Facebook's fastText library is now optimized for mobile". TechCrunch. Retrieved 12 January 2018.
  2. ^ Onur Çelebi (2020-04-28). "facebookresearch/fastText/releases/tag/v0.9.2". Facebook. Retrieved 2020-11-21.
  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. ^ "Wiki word vectors". fastText. Retrieved 26 November 2020.
  9. ^ "References · fastText". fasttext.cc. Retrieved 2021-09-08.
  10. ^ Bojanowski, Piotr; Grave, Edouard; Joulin, Armand; Mikolov, Tomas (2017-06-19). "Enriching Word Vectors with Subword Information". arXiv:1607.04606 [cs.CL].
  11. ^ Joulin, Armand; Grave, Edouard; Bojanowski, Piotr; Mikolov, Tomas (2016-08-09). "Bag of Tricks for Efficient Text Classification". arXiv:1607.01759 [cs.CL].
  12. ^ Joulin, Armand; Grave, Edouard; Bojanowski, Piotr; Douze, Matthijs; Jégou, Hérve; Mikolov, Tomas (2016-12-12). "FastText.zip: Compressing text classification models". arXiv:1612.03651 [cs.CL].
[edit]
Stub icon

This free and open-source software article is a stub. You can help Wikipedia by expanding it.

Retrieved from "https://en.wikipedia.org/w/index.php?title=FastText&oldid=1194745709"