방법 비교
선택한 방법을 나란히 검토하세요. 서로 다른 행은 강조 표시됩니다.
| 약한 지도 BERT 기반 분류× | BERT 기반 준지도 학습 분류× | |
|---|---|---|
| 분야 | 딥러닝 | 딥러닝 |
| 계열 | Machine learning | Machine learning |
| 기원 연도≠ | 2017–2020 | 2019–2020 |
| 창시자≠ | Multiple (Ratner et al. for weak supervision framework; Meng et al. for BERT integration) | Multiple groups (Xie et al.; Chen et al.; Devlin et al. for BERT base) |
| 유형≠ | Weakly supervised fine-tuning of pre-trained language model | Semi-supervised fine-tuning of pre-trained transformer |
| 원전≠ | Meng, Y., Zhang, Y., Huang, J., Xiong, C., Ji, H., Zhang, C., & Han, J. (2020). Text Classification Using Label Names Only: A Language Model Self-Training Approach. Proceedings of EMNLP 2020, 9006–9017. 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 ↗ |
| 별칭 | WS-BERT, BERT with weak supervision, label-efficient BERT classification, noisy-label BERT fine-tuning | Semi-supervised BERT, BERT SSL Classification, BERT with Unlabeled Data, BERT Semi-supervised Fine-tuning |
| 관련 | 6 | 6 |
| 요약≠ | Weakly supervised BERT-based classification adapts BERT to text classification tasks when only noisy, heuristic, or programmatically generated labels are available instead of clean human annotations. It combines weak supervision frameworks — such as labeling functions and data programming — with BERT's pre-trained language representations to achieve robust classification without expensive hand-labeling. | 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. |
| ScholarGate데이터셋 ↗ |
|
|