Comparer des méthodes
Examinez les méthodes sélectionnées côte à côte ; les lignes qui diffèrent sont mises en évidence.
| Classification faiblement supervisée basée sur RoBERTa× | Classification par BERT sous supervision faible× | |
|---|---|---|
| Domaine | Apprentissage profond | Apprentissage profond |
| Famille | Machine learning | Machine learning |
| Année d'origine≠ | 2019–2020 | 2017–2020 |
| Auteur d'origine≠ | Liu et al. (RoBERTa, 2019); weak supervision paradigm: Ratner et al. (2016–2020) | Multiple (Ratner et al. for weak supervision framework; Meng et al. for BERT integration) |
| Type≠ | Pretrained transformer classifier with weak supervision | Weakly supervised fine-tuning of pre-trained language model |
| Source fondatrice≠ | Liu, Y., Ott, M., Goyal, N., Du, J., Joshi, M., Chen, D., Levy, O., Lewis, M., Zettlemoyer, L., & Stoyanov, V. (2019). RoBERTa: A Robustly Optimized BERT Pretraining Approach. arXiv:1907.11692. link ↗ | 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 ↗ |
| Alias | WS-RoBERTa, RoBERTa with weak supervision, weakly supervised transformer classification, noisy-label RoBERTa classifier | WS-BERT, BERT with weak supervision, label-efficient BERT classification, noisy-label BERT fine-tuning |
| Apparentées≠ | 5 | 6 |
| Résumé≠ | Weakly supervised RoBERTa-based classification combines the RoBERTa pretrained transformer with weak supervision — programmatic or heuristic labeling sources — to train powerful text classifiers without requiring a fully hand-labeled dataset. Labeling functions, distant supervision, or crowd-sourced signals generate noisy labels that are aggregated and used to fine-tune RoBERTa for downstream classification tasks. | 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. |
| ScholarGateJeu de données ↗ |
|
|