So sánh phương pháp
Xem các phương pháp đã chọn cạnh nhau; những hàng khác biệt được làm nổi bật.
| Mạng nơ-ron hồi quy đa ngôn ngữ× | Transformer đa ngôn ngữ× | |
|---|---|---|
| Lĩnh vực | Học sâu | Học sâu |
| Họ | Machine learning | Machine learning |
| Năm ra đời≠ | 1990–2010s | 2019–2020 |
| Người khởi xướng≠ | Elman, J. L. (RNN); multilingual extension by NLP community | Devlin et al. (mBERT); Conneau et al. (XLM-R) |
| Loại≠ | Sequential model (cross-lingual) | Pre-trained cross-lingual language model |
| Công trình gốc≠ | Elman, J. L. (1990). Finding structure in time. Cognitive Science, 14(2), 179–211. DOI ↗ | 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. DOI ↗ |
| Tên gọi khác | Multilingual RNN, Cross-lingual RNN, Multi-language RNN, MRNN | multilingual LM, cross-lingual transformer, mBERT-style model, multilingual pre-trained model |
| Liên quan≠ | 5 | 4 |
| Tóm tắt≠ | 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. | 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. |
| ScholarGateBộ dữ liệu ↗ |
|
|