Porovnat metody

	Jemně doladěný Doc2Vec	Doc2Vec
Obor	Hluboké učení	Dolování textu
Rodina	Machine learning	Process / pipeline
Rok vzniku	2014 (base); fine-tuning practice ca. 2015	2014
Tvůrce	Le, Q. V. & Mikolov, T. (Doc2Vec base); fine-tuning practice adopted by the NLP community ca. 2015–2017	Quoc V. Le & Tomas Mikolov
Typ	Representation learning / transfer learning	Document-embedding representation learning
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.
Další názvy	fine-tuned Paragraph Vector, domain-adapted Doc2Vec, PV fine-tuning, Doc2Vec transfer learning	paragraph vector, document embeddings, Doc2Vec Belge Gömülmeleri
Příbuzné	5	4
Shrnutí	Fine-Tuned Doc2Vec adapts a pre-trained Paragraph Vector (Doc2Vec) model by continuing its training on a target corpus, producing document embeddings that capture both the general language knowledge of the original training and the vocabulary and style of the new domain. It is used for text classification, semantic similarity, and clustering when labeled data are scarce but unlabeled domain text is available.	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.