Сравнение на методи

	Слабо контролирано отговаряне на въпроси	Полуавтоматично отговаряне на въпроси
Област	Дълбоко обучение	Дълбоко обучение
Семейство	Machine learning	Machine learning
Година на възникване	2017–2019	2006–2020
Създател	Multiple authors (Clark, Gardner, Min et al.)	Multiple (Chapelle et al.; Zhu; Clark et al. for NLP applications)
Тип	Weakly supervised NLP model	Semi-supervised learning applied to extractive/generative QA
Основополагащ източник	Clark, C., & Gardner, M. (2018). Simple and Effective Multi-Paragraph Reading Comprehension. In Proceedings of ACL 2018, pp. 845–855. Association for Computational Linguistics.	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.
Други названия	WS-QA, distantly supervised QA, noisy-label question answering, indirect supervision QA	Semi-supervised QA, Self-training for QA, Pseudo-labeled Question Answering, SSL-QA
Свързани	4	6
Резюме	Weakly supervised question answering (WS-QA) trains neural reading-comprehension models using indirect or automatically derived answer labels rather than expensive human-annotated span annotations. By exploiting distant supervision, heuristic labeling, or answer-presence signals, WS-QA makes QA feasible in domains and languages where full annotation is impractical.	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.