Сравнение методов

	Слабо контролируемое извлечение ответов на вопросы	Дообученное вопросно-ответное извлечение
Область	Глубокое обучение	Глубокое обучение
Семейство	Machine learning	Machine learning
Год появления	2017–2019	2016–2019
Автор метода	Multiple authors (Clark, Gardner, Min et al.)	Devlin et al. (BERT); Rajpurkar et al. (SQuAD benchmark)
Тип	Weakly supervised NLP model	Transfer learning / fine-tuning for extractive or generative QA
Основополагающий источник	Clark, C., & Gardner, M. (2018). Simple and Effective Multi-Paragraph Reading Comprehension. In Proceedings of ACL 2018, pp. 845–855. Association for Computational Linguistics.	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.
Другие названия	WS-QA, distantly supervised QA, noisy-label question answering, indirect supervision QA	fine-tuned QA, neural QA with fine-tuning, extractive QA fine-tuning, reading comprehension fine-tuning
Связанные	4	5
Сводка	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.	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.