Methoden vergleichen

	Weakly supervised question answering	Semi-supervised Question Answering
Fachgebiet	Deep Learning	Deep Learning
Familie	Machine learning	Machine learning
Entstehungsjahr	2017–2019	2006–2020
Urheber	Multiple authors (Clark, Gardner, Min et al.)	Multiple (Chapelle et al.; Zhu; Clark et al. for NLP applications)
Typ	Weakly supervised NLP model	Semi-supervised learning applied to extractive/generative QA
Wegweisende Quelle	Clark, C., & Gardner, M. (2018). Simple and Effective Multi-Paragraph Reading Comprehension. In Proceedings of ACL 2018, pp. 845–855. Association for Computational Linguistics.	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.
Aliasnamen	WS-QA, distantly supervised QA, noisy-label question answering, indirect supervision QA	Semi-supervised QA, Self-training for QA, Pseudo-labeled Question Answering, SSL-QA
Verwandt	4	6
Zusammenfassung	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.	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.