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。
| 微调问答× | 微调文本摘要× | |
|---|---|---|
| 领域 | 深度学习 | 深度学习 |
| 方法族 | Machine learning | Machine learning |
| 起源年份≠ | 2016–2019 | 2019–2020 |
| 提出者≠ | Devlin et al. (BERT); Rajpurkar et al. (SQuAD benchmark) | Lewis et al. (BART); Zhang et al. (PEGASUS); Raffel et al. (T5) |
| 类型≠ | Transfer learning / fine-tuning for extractive or generative QA | Fine-tuned sequence-to-sequence neural model |
| 开创性文献≠ | 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, 4171–4186. DOI ↗ | Zhang, J., Zhao, Y., Saleh, M., & Liu, P. J. (2020). PEGASUS: Pre-training with Extracted Gap-sentences for Abstractive Summarization. Proceedings of the 37th International Conference on Machine Learning (ICML), 119, 11328–11339. link ↗ |
| 别名 | fine-tuned QA, neural QA with fine-tuning, extractive QA fine-tuning, reading comprehension fine-tuning | Fine-tuned summarization model, Abstractive summarization via fine-tuning, Seq2Seq fine-tuning for summarization, BART/T5/PEGASUS fine-tuning |
| 相关 | 5 | 5 |
| 摘要≠ | Fine-Tuned Question Answering adapts a large pre-trained language model — such as BERT, RoBERTa, or a GPT-family model — to answer natural-language questions over a given context passage or knowledge base. The model learns to locate answer spans or generate free-form answers by continuing training on labeled QA pairs after general-purpose pre-training. | Fine-Tuned Text Summarization adapts a large pre-trained sequence-to-sequence model — such as BART, T5, or PEGASUS — to generate concise summaries of documents by training on domain-specific (document, summary) pairs. The approach yields substantially more fluent and faithful summaries than extractive or generic approaches by leveraging knowledge encoded in billions of pre-training tokens. |
| ScholarGate数据集 ↗ |
|
|