Porovnat metody

	Slabě dohlížený Word2Vec	Doc2Vec
Obor	Hluboké učení	Dolování textu
Rodina	Machine learning	Process / pipeline
Rok vzniku	2013–2016	2014
Tvůrce	Mikolov et al. (Word2Vec); weak supervision framework: Ratner et al.	Quoc V. Le & Tomas Mikolov
Typ	Word embedding with noisy/programmatic labels	Document-embedding representation learning
Původní zdroj	Mikolov, T., Sutskever, I., Chen, K., Corrado, G., & Dean, J. (2013). Distributed representations of words and phrases and their compositionality. Advances in Neural Information Processing Systems, 26.	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	WS-Word2Vec, weakly-supervised word embeddings, weak-label Word2Vec, semi-noisy Word2Vec	paragraph vector, document embeddings, Doc2Vec Belge Gömülmeleri
Příbuzné	6	4
Shrnutí	Weakly Supervised Word2Vec trains Word2Vec-style embeddings using automatically generated, noisy, or heuristic labels rather than costly manual annotation. By leveraging labeling functions, distant supervision, or keyword-based rules to assign soft labels, the approach enables domain-adapted word representations even when large manually annotated corpora are unavailable.	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.