Comparar métodos

	Resposta a Perguntas com Supervisão Fraca	Question Answering Ajustado
Área	Aprendizado profundo	Aprendizado profundo
Família	Machine learning	Machine learning
Ano de origem	2017–2019	2016–2019
Autor original	Multiple authors (Clark, Gardner, Min et al.)	Devlin et al. (BERT); Rajpurkar et al. (SQuAD benchmark)
Tipo	Weakly supervised NLP model	Transfer learning / fine-tuning for extractive or generative QA
Fonte seminal	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.
Outros nomes	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
Relacionados	4	5
Resumo	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.