Сравнение методов

	Doc2Vec	Распространение меток	Word2Vec
Область	Интеллектуальный анализ текста	Машинное обучение	Интеллектуальный анализ текста
Семейство	Process / pipeline	Machine learning	Process / pipeline
Год появления	2014	2002	2013
Автор метода	Quoc V. Le & Tomas Mikolov	Zhu, X. & Ghahramani, Z.	Tomas Mikolov et al.
Тип	Document-embedding representation learning	Graph-based semi-supervised classification	Neural word-embedding model
Основополагающий источник	Le, Q. V. & Mikolov, T. (2014). Distributed Representations of Sentences and Documents. Proceedings of the 31st International Conference on Machine Learning (ICML), 1188-1196.	Zhu, X., & Ghahramani, Z. (2002). Learning from labeled and unlabeled data with label propagation. Technical Report CMU-CALD-02-107, Carnegie Mellon University.	Mikolov, T., Chen, K., Corrado, G. & Dean, J. (2013). Efficient Estimation of Word Representations in Vector Space.
Другие названия	paragraph vector, document embeddings, Doc2Vec Belge Gömülmeleri	LP, label spreading, graph-based semi-supervised learning, harmonic label propagation	word embeddings, skip-gram, continuous bag-of-words, Word2Vec Kelime Gömülmeleri
Связанные	4	3	4
Сводка	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.	Label Propagation is a graph-based semi-supervised learning algorithm introduced by Zhu and Ghahramani in 2002 that spreads class labels from a small set of labeled nodes to a large set of unlabeled nodes by iteratively diffusing label information along the edges of a similarity graph, exploiting the manifold structure of the data.	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.