Porovnat metody
Prohlédněte si vybrané metody vedle sebe; řádky, které se liší, jsou zvýrazněny.
| Polu-supervizované odpovídání na otázky× | Polu-dohledová klasifikace založená na BERT× | |
|---|---|---|
| Obor | Hluboké učení | Hluboké učení |
| Rodina | Machine learning | Machine learning |
| Rok vzniku≠ | 2006–2020 | 2019–2020 |
| Tvůrce≠ | 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) |
| Typ≠ | Semi-supervised learning applied to extractive/generative QA | Semi-supervised fine-tuning of pre-trained transformer |
| Původní zdroj≠ | 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. link ↗ | 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. link ↗ |
| Další názvy | 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 |
| Příbuzné | 6 | 6 |
| Shrnutí≠ | 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. |
| ScholarGateDatová sada ↗ |
|
|