Comparer des méthodes

	Autoencodeur variationnel multilingue	Réseau de neurones récurrent multilingue
Domaine	Apprentissage profond	Apprentissage profond
Famille	Machine learning	Machine learning
Année d'origine	2017-2018	1990–2010s
Auteur d'origine	Multiple research groups (Lample, Conneau et al.; Zhao et al.)	Elman, J. L. (RNN); multilingual extension by NLP community
Type	Generative latent-variable model	Sequential model (cross-lingual)
Source fondatrice	Zhao, T., Zhang, Y., & Eskenazi, M. (2018). Zero-shot dialog generation with cross-domain latent actions. In Proceedings of the 19th Annual SIGdial Meeting on Discourse and Dialogue (pp. 1-10). ACL.	Elman, J. L. (1990). Finding structure in time. Cognitive Science, 14(2), 179–211.
Alias	ML-VAE, cross-lingual VAE, multilingual latent variable model, multilingual generative autoencoder	Multilingual RNN, Cross-lingual RNN, Multi-language RNN, MRNN
Apparentées	5	5
Résumé	A Multilingual Variational Autoencoder (ML-VAE) extends the standard VAE framework to handle multiple languages within a shared probabilistic latent space. Language-specific encoders map text from each language into a common continuous representation, while language-specific decoders reconstruct or translate that text. This enables cross-lingual generation, style transfer, and representation learning with or without parallel corpora.	A Multilingual Recurrent Neural Network (Multilingual RNN) applies the standard RNN architecture — which processes sequences step by step while maintaining a hidden state — to data spanning two or more languages. By training on multilingual corpora or sharing parameters across languages, the model learns cross-lingual sequence representations useful for translation, tagging, classification, and language modeling tasks.