手法を比較

	FastText	ナイーブベイズ	Word2Vec
分野	深層学習	機械学習	テキストマイニング
系統	Machine learning	Machine learning	Process / pipeline
提唱年	2016	1997	2013
提唱者	Joulin, A.; Bojanowski, P.; Grave, E.; Mikolov, T. (Facebook AI Research)	Mitchell, T. M. (textbook treatment)	Tomas Mikolov et al.
種類	Subword embedding model and linear text classifier	Probabilistic classifier (Bayes' theorem with conditional independence)	Neural word-embedding model
原典	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.	Mitchell, T. M. (1997). Machine Learning. McGraw-Hill. ISBN: 978-0070428072	Mikolov, T., Chen, K., Corrado, G. & Dean, J. (2013). Efficient Estimation of Word Representations in Vector Space.
別名	fastText, fast text, subword embedding, character n-gram embedding	Naive Bayes Sınıflandırıcı, naive bayes classifier, simple Bayes, Gaussian Naive Bayes	word embeddings, skip-gram, continuous bag-of-words, Word2Vec Kelime Gömülmeleri
関連	2	4	4
概要	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.	Naive Bayes is a fast probabilistic classifier that applies Bayes' theorem while assuming that the features are conditionally independent given the class — a method given its standard machine-learning treatment in Tom Mitchell's 1997 textbook Machine Learning. Despite this simplifying ('naive') assumption, it is quick to train and often surprisingly accurate.	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.