विधियों की तुलना करें

	स्व-पर्यवेक्षित Word2Vec	फास्टटेक्स्ट	GloVe Embeddings
क्षेत्र	गहन अधिगम	गहन अधिगम	पाठ खनन
परिवार	Machine learning	Machine learning	Process / pipeline
उद्भव वर्ष	2013	2016	2014
प्रवर्तक	Mikolov, T., Chen, K., Corrado, G., & Dean, J.	Joulin, A.; Bojanowski, P.; Grave, E.; Mikolov, T. (Facebook AI Research)	Pennington, Socher & Manning
प्रकार	Self-supervised neural word embedding	Subword embedding model and linear text classifier	Static word-embedding model
मौलिक स्रोत	Mikolov, T., Chen, K., Corrado, G., & Dean, J. (2013). Efficient estimation of word representations in vector space. In Proceedings of the International Conference on Learning Representations (ICLR 2013).	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.	Pennington, J., Socher, R. & Manning, C. D. (2014). GloVe: Global Vectors for Word Representation. EMNLP.
उपनाम	Word2Vec, word embeddings, Skip-gram model, CBOW model	fastText, fast text, subword embedding, character n-gram embedding	GloVe, global vectors, GloVe Kelime Gömülmeleri
संबंधित	3	2	3
सारांश	Word2Vec is a shallow neural network model introduced by Mikolov et al. (2013) that learns dense vector representations of words from large unlabeled text corpora using self-supervised objectives. By training a model to predict surrounding context words (Skip-gram) or a target word from its context (CBOW), it captures rich semantic and syntactic regularities in continuous vector space without any manual annotation.	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.	GloVe (Global Vectors for Word Representation) is a static word-embedding model introduced by Pennington, Socher and Manning (2014) that learns word vectors directly from global word-word co-occurrence statistics gathered across an entire corpus. The resulting vectors place semantically related words close together and perform strongly on semantic analogy tasks.