Comparar métodos
Revisa los métodos seleccionados uno junto a otro; las filas que difieren aparecen resaltadas.
| Clasificación basada en BERT con supervisión débil× | Clasificación basada en BERT adaptada al dominio× | |
|---|---|---|
| Campo | Aprendizaje profundo | Aprendizaje profundo |
| Familia | Machine learning | Machine learning |
| Año de origen≠ | 2017–2020 | 2019–2020 |
| Autor original≠ | Multiple (Ratner et al. for weak supervision framework; Meng et al. for BERT integration) | Gururangan et al. (2020); earlier domain-specific instances include Lee et al. (2020) — BioBERT |
| Tipo≠ | Weakly supervised fine-tuning of pre-trained language model | Domain-adaptive pre-training followed by supervised fine-tuning |
| Fuente seminal≠ | 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 ↗ | Gururangan, S., Marasovic, A., Swayamdipta, S., Lo, K., Beltagy, I., Downey, D., & Smith, N. A. (2020). Don't Stop Pretraining: Adapt Language Models to Domains and Tasks. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics (ACL 2020), 8342–8360. DOI ↗ |
| Alias | WS-BERT, BERT with weak supervision, label-efficient BERT classification, noisy-label BERT fine-tuning | DAPT BERT classification, domain-adaptive pre-training, domain-specific BERT fine-tuning, BERT DAPT |
| Relacionados | 6 | 6 |
| Resumen≠ | 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. | Domain-adaptive BERT-based classification extends the standard fine-tuning pipeline by first continuing BERT's masked-language-model pre-training on a large corpus of in-domain unlabeled text, then fine-tuning the adapted model on labeled examples for the target classification task. This two-stage approach closes the vocabulary and distributional gap between BERT's general pre-training corpus and specialized domains such as biomedicine, law, finance, or social-media text. |
| ScholarGateConjunto de datos ↗ |
|
|