方法对比

	多语言多层感知机	多语言 Transformer
领域	深度学习	深度学习
方法族	Machine learning	Machine learning
起源年份	2010s	2019–2020
提出者	McCulloch & Pitts / Rumelhart et al. (MLP); multilingual application became standard in NLP from the 2010s onward	Devlin et al. (mBERT); Conneau et al. (XLM-R)
类型	Feedforward neural network (multilingual variant)	Pre-trained cross-lingual language model
开创性文献	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.	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.
别名	Multilingual MLP, cross-lingual MLP, multilingual feedforward network, multilingual FFNN	multilingual LM, cross-lingual transformer, mBERT-style model, multilingual pre-trained model
相关	4	4
摘要	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 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.