Talk:FastText
 | This article is rated Stub-class on Wikipedia's content assessment scale. It is of interest to the following WikiProjects: | |||||||||||||
| ||||||||||||||
Contested deletion edit
This article should not be speedily deleted for lack of asserted importance because it's a widely used machine learning algorithm used to create word embeddings; here's 350 academic papers citing the technology, demonstrating significant coverage in reliable sources that are independent of the subject as called for in WP:GNG. One creates a WP:stub like this for lack of time to create a beautiful article; instead of nominating for speedy deletion, perhaps fixing the article would be a better use of time. Topical essays: WP:DEMOLISH & WP:CHANCE --Justin Ormont (talk) 13:30, 12 January 2018 (UTC)
- Wikipedia is an encyclopedia that summarizes what independent, reliable sources say about a topic. If you don't include any sources then we can't have an article, consider using the WP:AFC process if you want time to work on an article. Theroadislong (talk) 13:39, 12 January 2018 (UTC)
fastText does not use a neural network for word embedding edit
I removed the claim "fastText uses a neural network for word embedding" since the Bag of Tricks paper says it is effectively a linear classifier. Wqwt (talk) 19:58, 8 September 2021 (UTC)