手法を比較

	半教師ありDoc2Vec	ラベル伝播	Word2Vec
分野	深層学習	機械学習	テキストマイニング
系統	Machine learning	Machine learning	Process / pipeline
提唱年	2014–2017	2002	2013
提唱者	Le, Q. V. & Mikolov, T. (base Doc2Vec); semi-supervised extensions by various authors circa 2015–2019	Zhu, X. & Ghahramani, Z.	Tomas Mikolov et al.
種類	Semi-supervised representation learning	Graph-based semi-supervised classification	Neural word-embedding model
原典	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.	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.
別名	Semi-supervised Paragraph Vector, SS-Doc2Vec, Label-guided PV-DBOW, Semi-supervised PV-DM	LP, label spreading, graph-based semi-supervised learning, harmonic label propagation	word embeddings, skip-gram, continuous bag-of-words, Word2Vec Kelime Gömülmeleri
関連	3	3	4
概要	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.	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.