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。
| 半监督问答× | 自监督问答× | |
|---|---|---|
| 领域 | 深度学习 | 深度学习 |
| 方法族 | Machine learning | Machine learning |
| 起源年份≠ | 2006–2020 | 2019 |
| 提出者≠ | Multiple (Chapelle et al.; Zhu; Clark et al. for NLP applications) | Lewis, P.; Alberti, C. et al. (multiple independent groups ~2019) |
| 类型≠ | Semi-supervised learning applied to extractive/generative QA | Self-supervised NLP training paradigm |
| 开创性文献≠ | Clark, K., Luong, M.-T., Le, Q. V., & Manning, C. D. (2020). ELECTRA: Pre-training Text Encoders as Discriminators Rather Than Generators. In Proceedings of ICLR 2020. link ↗ | Lewis, P., Denoyer, L., & Riedel, S. (2019). Unsupervised Question Answering by Cloze Translation. Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics (ACL 2019), pp. 4896–4910. DOI ↗ |
| 别名 | Semi-supervised QA, Self-training for QA, Pseudo-labeled Question Answering, SSL-QA | SSQA, unsupervised question answering, self-supervised QA, zero-label question answering |
| 相关≠ | 6 | 1 |
| 摘要≠ | Semi-supervised question answering (QA) trains a model on a small labeled set of question-answer pairs, then generates pseudo-labels on a large unlabeled corpus and retrains iteratively. This self-training loop dramatically increases effective training data without the cost of full manual annotation, achieving strong performance on reading comprehension, open-domain QA, and machine reading tasks. | Self-supervised Question Answering (SSQA) is a training paradigm that automatically generates question-answer pairs from unlabeled text — using cloze translation, span masking, or neural question generation — to train QA models without any human-labeled data. It enables high-quality reading comprehension systems even when annotated datasets are scarce or domain-specific. |
| ScholarGate数据集 ↗ |
|
|