Porovnat metody

	FastText	Word2Vec
Obor	Hluboké učení	Dolování textu
Rodina	Machine learning	Process / pipeline
Rok vzniku	2016	2013
Tvůrce	Joulin, A.; Bojanowski, P.; Grave, E.; Mikolov, T. (Facebook AI Research)	Tomas Mikolov et al.
Typ	Subword embedding model and linear text classifier	Neural word-embedding model
Původní zdroj	Joulin, A., Grave, E., Bojanowski, P. & Mikolov, T. (2017). Bag of Tricks for Efficient Text Classification. In Proceedings of EACL 2017, Short Papers, pp. 427–431. ACL.	Mikolov, T., Chen, K., Corrado, G. & Dean, J. (2013). Efficient Estimation of Word Representations in Vector Space.
Další názvy	fastText, fast text, subword embedding, character n-gram embedding	word embeddings, skip-gram, continuous bag-of-words, Word2Vec Kelime Gömülmeleri
Příbuzné	2	4
Shrnutí	FastText is a word embedding and text classification framework developed by Facebook AI Research (Joulin, Bojanowski, Grave, and Mikolov, 2016–2017) that represents each word as the sum of its character n-gram vectors, allowing it to construct meaningful representations for unseen and morphologically rich words and to perform near state-of-the-art text classification orders of magnitude faster than deep neural network alternatives.	Word2Vec is a neural word-embedding technique introduced by Mikolov and colleagues in 2013 that maps each word in a text corpus to a dense numeric vector. Words that appear in similar contexts end up close together in the vector space, so the embeddings capture semantic similarity that can be measured arithmetically.