Linganisha mbinu

	Kujibu Maswali Kwa Urekebishaji wa Kikoa	Maswali yanayojibiwa kwa usahihi
Nyanja	Ujifunzaji wa Kina	Ujifunzaji wa Kina
Familia	Machine learning	Machine learning
Mwaka wa asili	2019–2020	2016–2019
Mwanzilishi	Multiple (e.g., Garg et al.; Yue et al.)	Devlin et al. (BERT); Rajpurkar et al. (SQuAD benchmark)
Aina	Domain adaptation for extractive/generative QA	Transfer learning / fine-tuning for extractive or generative QA
Chanzo asilia	Garg, S., Vu, T., & Moschitti, A. (2020). TANDA: Transfer and Adapt Pre-Trained Transformer Models for Answer Sentence Selection. Proceedings of the AAAI Conference on Artificial Intelligence, 34(5), 7780–7788.	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.
Majina mbadala	DA-QA, domain-adapted QA, domain-specific question answering, cross-domain question answering	fine-tuned QA, neural QA with fine-tuning, extractive QA fine-tuning, reading comprehension fine-tuning
Zinazohusiana	6	5
Muhtasari	Domain-adaptive Question Answering (DA-QA) adapts a pre-trained language model — typically BERT or RoBERTa — first trained on general QA benchmarks such as SQuAD to answer questions accurately in a new target domain (e.g., biomedical, legal, financial) where labelled data is scarce. Combining domain-adaptive pre-training with task fine-tuning yields substantially stronger performance than direct fine-tuning alone.	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.