Porovnat metody

	Semi-supervised Doc2Vec	Doc2Vec	Word2Vec
Obor	Hluboké učení	Dolování textu	Dolování textu
Rodina	Machine learning	Process / pipeline	Process / pipeline
Rok vzniku	2014–2017	2014	2013
Tvůrce	Le, Q. V. & Mikolov, T. (base Doc2Vec); semi-supervised extensions by various authors circa 2015–2019	Quoc V. Le & Tomas Mikolov	Tomas Mikolov et al.
Typ	Semi-supervised representation learning	Document-embedding representation learning	Neural word-embedding model
Původní zdroj	Le, Q. V., & Mikolov, T. (2014). Distributed Representations of Sentences and Documents. Proceedings of the 31st International Conference on Machine Learning (ICML 2014), PMLR 32(2), 1188–1196.	Le, Q. V. & Mikolov, T. (2014). Distributed Representations of Sentences and Documents. Proceedings of the 31st International Conference on Machine Learning (ICML), 1188-1196.	Mikolov, T., Chen, K., Corrado, G. & Dean, J. (2013). Efficient Estimation of Word Representations in Vector Space.
Další názvy	Semi-supervised Paragraph Vector, SS-Doc2Vec, Label-guided PV-DBOW, Semi-supervised PV-DM	paragraph vector, document embeddings, Doc2Vec Belge Gömülmeleri	word embeddings, skip-gram, continuous bag-of-words, Word2Vec Kelime Gömülmeleri
Příbuzné	3	4	4
Shrnutí	Semi-supervised Doc2Vec extends the Paragraph Vector framework of Le and Mikolov (2014) by training dense document embeddings on both labeled and unlabeled corpora simultaneously, using available class labels as an auxiliary signal to steer the representation toward task-relevant structure while still exploiting the full unlabeled collection for generalization.	Doc2Vec, also known as Paragraph Vector, is a representation-learning method introduced by Le and Mikolov (2014) that maps whole documents to fixed-length dense vectors. These vectors place similar documents close together in space, supporting document comparison and classification.	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.