Comparer des méthodes

	LSTM multilingue	Transformeur multilingue
Domaine	Apprentissage profond	Apprentissage profond
Famille	Machine learning	Machine learning
Année d'origine	1997 (LSTM); multilingual NLP applications from ~2016	2019–2020
Auteur d'origine	Hochreiter, S. & Schmidhuber, J. (LSTM base); multilingual application by the NLP community from ~2016	Devlin et al. (mBERT); Conneau et al. (XLM-R)
Type	Recurrent neural network (sequence model)	Pre-trained cross-lingual language model
Source fondatrice	Hochreiter, S. & Schmidhuber, J. (1997). Long Short-Term Memory. Neural Computation, 9(8), 1735–1780.	Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2019). BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. Proceedings of NAACL-HLT 2019, pp. 4171–4186. Association for Computational Linguistics.
Alias	Multilingual LSTM, Cross-lingual LSTM, Multi-language LSTM, Multilingual Recurrent Network	multilingual LM, cross-lingual transformer, mBERT-style model, multilingual pre-trained model
Apparentées	5	4
Résumé	A Multilingual LSTM is a Long Short-Term Memory recurrent network trained or fine-tuned to process sequences in multiple languages, typically by sharing a single model across language-specific or joint subword embeddings. It captures long-range dependencies in text and is applied to multilingual classification, named entity recognition, sentiment analysis, and sequence labeling.	A multilingual transformer is a pre-trained language model built on the transformer architecture and trained jointly on text from dozens to over one hundred languages. Models such as mBERT and XLM-RoBERTa learn shared cross-lingual representations, enabling zero-shot or few-shot transfer: a model fine-tuned on English data can often be applied directly to French, German, Arabic, or Chinese without language-specific labels.