Сравнение методов
Просматривайте выбранные методы рядом; строки с различиями подсвечены.
| Полуавтоматический анализ тональности× | Полуавтоматическая классификация на основе BERT× | |
|---|---|---|
| Область | Глубокое обучение | Глубокое обучение |
| Семейство | Machine learning | Machine learning |
| Год появления≠ | 2002–2008 | 2019–2020 |
| Автор метода≠ | Zhu, X.; Pang, B. & Lee, L. (foundational works) | Multiple groups (Xie et al.; Chen et al.; Devlin et al. for BERT base) |
| Тип≠ | Semi-supervised classification | Semi-supervised fine-tuning of pre-trained transformer |
| Основополагающий источник≠ | Zhu, X. (2005). Semi-Supervised Learning Literature Survey. Technical Report 1530, Computer Sciences, University of Wisconsin-Madison. 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 ↗ |
| Другие названия | SSSA, semi-supervised opinion mining, label-propagation sentiment classification, self-training sentiment analysis | Semi-supervised BERT, BERT SSL Classification, BERT with Unlabeled Data, BERT Semi-supervised Fine-tuning |
| Связанные≠ | 4 | 6 |
| Сводка≠ | Semi-supervised sentiment analysis combines a small set of manually labeled text samples with a large pool of unlabeled text to train opinion classifiers. By propagating sentiment signals from labeled seeds to unlabeled data through self-training, label propagation, or consistency regularization, the approach achieves competitive accuracy without the cost of labeling large corpora. | 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. |
| ScholarGateНабор данных ↗ |
|
|