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。
| 多语言循环神经网络× | 长短期记忆网络（LSTM）× | |
|---|---|---|
| 领域 | 深度学习 | 深度学习 |
| 方法族 | Machine learning | Machine learning |
| 起源年份≠ | 1990–2010s | 1997 |
| 提出者≠ | Elman, J. L. (RNN); multilingual extension by NLP community | Hochreiter, S. & Schmidhuber, J. |
| 类型≠ | Sequential model (cross-lingual) | Recurrent neural network with gated memory cells |
| 开创性文献≠ | Elman, J. L. (1990). Finding structure in time. Cognitive Science, 14(2), 179–211. DOI ↗ | Hochreiter, S. & Schmidhuber, J. (1997). Long short-term memory. Neural Computation, 9(8), 1735–1780. DOI ↗ |
| 别名 | Multilingual RNN, Cross-lingual RNN, Multi-language RNN, MRNN | LSTM, LSTM network, LSTM-RNN, long short-term memory RNN |
| 相关≠ | 5 | 4 |
| 摘要≠ | 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. | Long Short-Term Memory (LSTM) is a gated recurrent neural network architecture introduced by Hochreiter and Schmidhuber in 1997. It was designed to learn dependencies across long sequences by using dedicated memory cells and three learned gates — forget, input, and output — that control what information is retained, updated, or passed forward at each time step. |
| ScholarGate数据集 ↗ |
|
|