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。
| 自然语言生成× | 机器翻译× | |
|---|---|---|
| 领域 | 文本挖掘 | 文本挖掘 |
| 方法族 | Process / pipeline | Process / pipeline |
| 起源年份≠ | 1970s (rule-based origins); 2000s (probabilistic); 2017+ (neural/transformer era) | — |
| 提出者≠ | Reiter & Dale (classical pipeline, 2000); Gatt & Krahmer (modern survey, 2018) | — |
| 类型≠ | NLP generative task — structured data to natural language | NLP text-to-text generation task |
| 开创性文献≠ | Gatt, A. & Krahmer, E. (2018). Survey of the State of the Art in Natural Language Generation: Core Tasks, Applications and Evaluation. Journal of Artificial Intelligence Research, 61, 65-170. link ↗ | Bahdanau, D., Cho, K. & Bengio, Y. (2015). Neural Machine Translation by Jointly Learning to Align and Translate. International Conference on Learning Representations (ICLR). link ↗ |
| 别名 | NLG, data-to-text, text generation, Doğal Dil Üretimi (NLG) | MT, neural machine translation, automatic translation, Makine Çevirisi (Machine Translation) |
| 相关≠ | 7 | 3 |
| 摘要≠ | Natural Language Generation (NLG) is the branch of natural language processing that automatically produces fluent, human-readable text from structured data, knowledge graphs, or semantic representations. Formalised in the classical pipeline by Reiter and Dale (2000) and surveyed comprehensively by Gatt and Krahmer (2018), NLG powers applications ranging from automated financial reporting and weather bulletins to data storytelling and conversational agents. | Machine translation (MT) is a natural-language-processing task that automatically converts text in one language into another. Modern MT is built on neural sequence-to-sequence models — the attention mechanism introduced by Bahdanau et al. (2015) and the transformer architecture of Vaswani et al. (2017) — and it widens access to sources for multilingual data analysis and research. |
| ScholarGate数据集 ↗ |
|
|