手法を比較

	多言語畳み込みニューラルネットワーク	多言語リカレントニューラルネットワーク
分野	深層学習	深層学習
系統	Machine learning	Machine learning
提唱年	2014–2016	1990–2010s
提唱者	Kim, Y. (seminal NLP CNN); multilingual extension by community	Elman, J. L. (RNN); multilingual extension by NLP community
種類	Deep learning classifier	Sequential model (cross-lingual)
原典	Kim, Y. (2014). Convolutional Neural Networks for Sentence Classification. Proceedings of EMNLP 2014, pp. 1746–1751.	Elman, J. L. (1990). Finding structure in time. Cognitive Science, 14(2), 179–211.
別名	ML-CNN, cross-lingual CNN, multilingual text CNN, multilingual ConvNet	Multilingual RNN, Cross-lingual RNN, Multi-language RNN, MRNN
関連	4	5
概要	A Multilingual CNN applies convolutional filters over token embeddings drawn from two or more languages, producing shared feature representations that enable a single model to classify, tag, or extract information across language boundaries without training separate models per language. It extends the standard text-CNN architecture with multilingual or cross-lingual input embeddings.	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.