Сравнение методов

	Полуавтоматическое ответы на вопросы	Самообучаемая система ответов на вопросы
Область	Глубокое обучение	Глубокое обучение
Семейство	Machine learning	Machine learning
Год появления	2006–2020	2019
Автор метода	Multiple (Chapelle et al.; Zhu; Clark et al. for NLP applications)	Lewis, P.; Alberti, C. et al. (multiple independent groups ~2019)
Тип	Semi-supervised learning applied to extractive/generative QA	Self-supervised NLP training paradigm
Основополагающий источник	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.	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.
Другие названия	Semi-supervised QA, Self-training for QA, Pseudo-labeled Question Answering, SSL-QA	SSQA, unsupervised question answering, self-supervised QA, zero-label question answering
Связанные	6	1
Сводка	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.