方法对比
并排查看您选择的方法；存在差异的行会高亮显示。
| 多语言生成对抗网络 (Multilingual GAN)× | 多语言循环神经网络× | |
|---|---|---|
| 领域 | 深度学习 | 深度学习 |
| 方法族 | Machine learning | Machine learning |
| 起源年份≠ | 2017–2019 | 1990–2010s |
| 提出者≠ | Goodfellow et al. (GAN); multilingual extensions by various authors from 2017 onward | Elman, J. L. (RNN); multilingual extension by NLP community |
| 类型≠ | Generative adversarial model with multilingual conditioning | Sequential model (cross-lingual) |
| 开创性文献≠ | Goodfellow, I., Pouget-Abadie, J., Mirza, M., Xu, B., Warde-Farley, D., Ozair, S., Courville, A., & Bengio, Y. (2014). Generative Adversarial Nets. Advances in Neural Information Processing Systems (NeurIPS), 27. link ↗ | Elman, J. L. (1990). Finding structure in time. Cognitive Science, 14(2), 179–211. DOI ↗ |
| 别名 | Multilingual GAN, Cross-lingual GAN, Multilingual Generative Adversarial Network, ML-GAN | Multilingual RNN, Cross-lingual RNN, Multi-language RNN, MRNN |
| 相关 | 5 | 5 |
| 摘要≠ | A Multilingual GAN pairs the generative adversarial framework with cross-lingual components — a shared encoder, language-conditioned generator, and a language discriminator — so that a single model can generate or align representations across multiple languages simultaneously. It is applied to cross-lingual text generation, machine translation, multilingual data augmentation, and language-invariant feature learning. | 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. |
| ScholarGate数据集 ↗ |
|
|