Linganisha mbinu
Pitia mbinu ulizochagua bega kwa bega; safu zinazotofautiana zinaangaziwa.
| Semi-supervised GAN× | Uainishaji wa BERT unaosaidiwa kwa nusu-msaada× | |
|---|---|---|
| Nyanja | Ujifunzaji wa Kina | Ujifunzaji wa Kina |
| Familia | Machine learning | Machine learning |
| Mwaka wa asili≠ | 2016 | 2019–2020 |
| Mwanzilishi≠ | Odena, A.; Salimans, T. et al. | Multiple groups (Xie et al.; Chen et al.; Devlin et al. for BERT base) |
| Aina≠ | Semi-supervised generative model | Semi-supervised fine-tuning of pre-trained transformer |
| Chanzo asilia≠ | Salimans, T., Goodfellow, I., Zaremba, W., Cheung, V., Radford, A., & Chen, X. (2016). Improved Techniques for Training GANs. Advances in Neural Information Processing Systems (NeurIPS), 29. 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 ↗ |
| Majina mbadala | SGAN, Semi-GAN, semi-supervised generative adversarial network, GAN-based semi-supervised learning | Semi-supervised BERT, BERT SSL Classification, BERT with Unlabeled Data, BERT Semi-supervised Fine-tuning |
| Zinazohusiana≠ | 5 | 6 |
| Muhtasari≠ | Semi-supervised GAN (SGAN) extends the standard GAN discriminator to simultaneously classify labeled examples into K real classes and detect generated fakes as a (K+1)-th class, letting the generator's synthetic data act as implicit regularization and allowing strong classifiers to be trained with very few labeled examples. | 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. |
| ScholarGateSeti ya data ↗ |
|
|