Krahasoni metodat

	Përgjigjja pyetjeve gjysmë-mbikëqyrur	Klasifikim i mbështetur në BERT me mbikëqyrje gjysmë-sistematike
Fusha	Mësimi i thellë	Mësimi i thellë
Familja	Machine learning	Machine learning
Viti i origjinës	2006–2020	2019–2020
Krijuesi	Multiple (Chapelle et al.; Zhu; Clark et al. for NLP applications)	Multiple groups (Xie et al.; Chen et al.; Devlin et al. for BERT base)
Lloji	Semi-supervised learning applied to extractive/generative QA	Semi-supervised fine-tuning of pre-trained transformer
Burimi themelues	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.	Xie, Q., Dai, Z., Hovy, E., Luong, T., & Le, Q. (2020). Unsupervised Data Augmentation for Consistency Training. Advances in Neural Information Processing Systems (NeurIPS), 33, 27780–27792.
Emërtime të tjera	Semi-supervised QA, Self-training for QA, Pseudo-labeled Question Answering, SSL-QA	Semi-supervised BERT, BERT SSL Classification, BERT with Unlabeled Data, BERT Semi-supervised Fine-tuning
Të lidhura	6	6
Përmbledhja	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.	Semi-supervised BERT-based classification fine-tunes a pre-trained BERT encoder on a small pool of labeled text examples while simultaneously leveraging a much larger body of unlabeled text — via consistency training, pseudo-labeling, or data augmentation — to produce high-quality classifiers even when manual annotation is scarce.