Comparer des méthodes
Examinez les méthodes sélectionnées côte à côte ; les lignes qui diffèrent sont mises en évidence.
| Word2Vec semi-supervisé× | Modèle de Topics LDA× | |
|---|---|---|
| Domaine | Apprentissage profond | Apprentissage profond |
| Famille | Machine learning | Machine learning |
| Année d'origine≠ | 2013–2015 | 2003 |
| Auteur d'origine≠ | Mikolov, T. et al. (Word2Vec); semi-supervised framing via Collobert & Weston and subsequent NLP literature | Blei, D. M., Ng, A. Y., & Jordan, M. I. |
| Type≠ | Semi-supervised representation learning | Probabilistic generative topic model |
| Source fondatrice≠ | Mikolov, T., Chen, K., Corrado, G., & Dean, J. (2013). Efficient Estimation of Word Representations in Vector Space. In Proceedings of ICLR 2013. link ↗ | Blei, D. M., Ng, A. Y., & Jordan, M. I. (2003). Latent Dirichlet Allocation. Journal of Machine Learning Research, 3, 993–1022. link ↗ |
| Alias | Word2Vec with semi-supervised learning, semi-supervised word embeddings, Word2Vec SSL, unsupervised pretraining with Word2Vec | LDA, Latent Dirichlet Allocation, LDA Topic Modeling, Dirichlet Topic Model |
| Apparentées≠ | 6 | 5 |
| Résumé≠ | Semi-supervised Word2Vec trains dense word representations on a large unlabeled corpus using Word2Vec (skip-gram or CBOW), then uses those embeddings as fixed or fine-tunable input features for a downstream classifier trained on a small labeled dataset. This two-stage process lets models benefit from abundant unlabeled text when labeled data is scarce. | Latent Dirichlet Allocation (LDA) is a probabilistic generative model introduced by Blei, Ng, and Jordan in 2003 that discovers hidden thematic structure in large text collections by representing each document as a mixture of latent topics and each topic as a probability distribution over vocabulary words. |
| ScholarGateJeu de données ↗ |
|
|