Porovnat metody

	Doménově adaptované Word2Vec	Doménově adaptované větné vnořené reprezentace
Obor	Hluboké učení	Hluboké učení
Rodina	Machine learning	Machine learning
Rok vzniku	2013–2016	2019–2020
Tvůrce	Mikolov, T. et al. (Word2Vec); domain adaptation practice emerged in NLP community ~2014–2016	Reimers, N. & Gurevych, I. (Sentence-BERT); Gururangan et al. (domain-adaptive pretraining)
Typ	Domain-adapted word embedding model	Domain-adaptive representation learning
Původní zdroj	Mikolov, T., Chen, K., Corrado, G., & Dean, J. (2013). Efficient estimation of word representations in vector space. In Proceedings of ICLR Workshop.	Reimers, N. & Gurevych, I. (2019). Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks. Proceedings of EMNLP-IJCNLP 2019, pp. 3982–3992.
Další názvy	domain-specific Word2Vec, domain-adapted word embeddings, domain Word2Vec, specialized Word2Vec	domain-adapted sentence transformers, domain-specific sentence embeddings, target-domain sentence representations, DAPT sentence embeddings
Příbuzné	5	6
Shrnutí	Domain-adaptive Word2Vec trains or fine-tunes Word2Vec embeddings on a domain-specific text corpus so that word vectors capture the specialized vocabulary, semantic relationships, and jargon of a target field — such as clinical medicine, legal text, financial reports, or scientific literature — rather than reflecting general-purpose web or news language.	Domain-adaptive sentence embeddings extend general-purpose sentence encoders — such as Sentence-BERT — by continuing their training on domain-specific text. The result is a fixed-length vector representation that captures both universal language understanding and the vocabulary, style, and semantic nuances of the target domain, improving downstream NLP tasks such as semantic search, clustering, and classification.