Talk:FastText

	This article is within the scope of WikiProject Software, a collaborative effort to improve the coverage of software on Wikipedia. If you would like to participate, please visit the project page, where you can join the discussion and see a list of open tasks.SoftwareWikipedia:WikiProject SoftwareTemplate:WikiProject Softwaresoftware articles
Low	This article has been rated as Low-importance on the project's importance scale.
	This article is supported by WikiProject Computing.

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)[reply]

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)[reply]

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)[reply]