Сравнение методов

	Многоязычный многослойный перцептрон	Многоязычная рекуррентная нейронная сеть
Область	Глубокое обучение	Глубокое обучение
Семейство	Machine learning	Machine learning
Год появления	2010s	1990–2010s
Автор метода	McCulloch & Pitts / Rumelhart et al. (MLP); multilingual application became standard in NLP from the 2010s onward	Elman, J. L. (RNN); multilingual extension by NLP community
Тип	Feedforward neural network (multilingual variant)	Sequential model (cross-lingual)
Основополагающий источник	Artetxe, M., & Schwartz, H. A. (2019). Massively Multilingual Sentence Embeddings for Zero-Shot Cross-Lingual Transfer and Beyond. Transactions of the Association for Computational Linguistics, 7, 597–610.	Elman, J. L. (1990). Finding structure in time. Cognitive Science, 14(2), 179–211.
Другие названия	Multilingual MLP, cross-lingual MLP, multilingual feedforward network, multilingual FFNN	Multilingual RNN, Cross-lingual RNN, Multi-language RNN, MRNN
Связанные	4	5
Сводка	A Multilingual MLP is a feedforward neural network trained on text from two or more languages, relying on shared or aligned input representations — such as multilingual word embeddings or subword vocabularies — so that a single model can process and classify text across languages without separate per-language networks.	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.