Порівняння методів

	Адаптація до домену для відповідей на запитання	Багатомовна відповідь на запитання
Галузь	Глибоке навчання	Глибоке навчання
Родина	Machine learning	Machine learning
Рік появи	2019–2020	2018–2020
Автор методу	Multiple (e.g., Garg et al.; Yue et al.)	Multiple groups; popularised via mBERT (Devlin et al., 2019) and XLM-R (Conneau et al., 2020)
Тип	Domain adaptation for extractive/generative QA	Extractive / generative QA across multiple languages
Основоположне джерело	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.	Artetxe, M., Ruder, S., & Yogatama, D. (2020). On the cross-lingual transferability of monolingual representations. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics (pp. 4623–4637). ACL.
Інші назви	DA-QA, domain-adapted QA, domain-specific question answering, cross-domain question answering	cross-lingual question answering, multilingual QA, multilingual MRC, cross-lingual machine reading comprehension
Пов'язані	6	4
Підсумок	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.	Multilingual question answering (QA) enables a model to read a passage and answer questions in multiple languages, often by fine-tuning a cross-lingual pretrained transformer such as mBERT or XLM-R on an annotated QA dataset in one language and transferring that capability zero-shot or few-shot to other languages. It is the standard approach for building multilingual reading-comprehension and open-domain QA systems.