Сравнение на методи

	Полуавтоматично отговаряне на въпроси	Фино настроено отговаряне на въпроси
Област	Дълбоко обучение	Дълбоко обучение
Семейство	Machine learning	Machine learning
Година на възникване	2006–2020	2016–2019
Създател	Multiple (Chapelle et al.; Zhu; Clark et al. for NLP applications)	Devlin et al. (BERT); Rajpurkar et al. (SQuAD benchmark)
Тип	Semi-supervised learning applied to extractive/generative QA	Transfer learning / fine-tuning for extractive or generative QA
Основополагащ източник	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.	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.
Други названия	Semi-supervised QA, Self-training for QA, Pseudo-labeled Question Answering, SSL-QA	fine-tuned QA, neural QA with fine-tuning, extractive QA fine-tuning, reading comprehension fine-tuning
Свързани	6	5
Резюме	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.	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.