Compară metode
Examinează metodele selectate una lângă alta; rândurile care diferă sunt evidențiate.
| Clasificare bazată pe RoBERTa explicabil× | Clasificare explicabilă bazată pe BERT× | |
|---|---|---|
| Domeniu | Învățare profundă | Învățare profundă |
| Familie | Machine learning | Machine learning |
| Anul apariției | 2019–2020 | 2019–2020 |
| Autorul original≠ | Liu et al. (RoBERTa, 2019); Lundberg & Lee (SHAP, 2017); Ribeiro et al. (LIME, 2016) | Devlin et al. (BERT); explainability methods by Lundberg & Lee (SHAP), Ribeiro et al. (LIME), Sundararajan et al. (Integrated Gradients) |
| Tip≠ | Pre-trained transformer classifier with post-hoc XAI | Pre-trained transformer classifier with post-hoc or intrinsic explainability |
| Sursa seminală≠ | 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 preprint arXiv:1907.11692. link ↗ | Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2019). BERT: Pre-training of deep bidirectional transformers for language understanding. Proceedings of NAACL-HLT 2019, pp. 4171–4186. DOI ↗ |
| Denumiri alternative | XAI-RoBERTa, Interpretable RoBERTa Classifier, RoBERTa with SHAP/LIME, Transparent RoBERTa NLP | XAI-BERT, interpretable BERT classifier, BERT with post-hoc explanation, transparent BERT classification |
| Înrudite≠ | 5 | 6 |
| Rezumat≠ | Explainable RoBERTa-based classification fine-tunes a RoBERTa transformer model on labeled text data and then applies post-hoc interpretability methods — such as SHAP, LIME, or attention analysis — to reveal which tokens or features drove each prediction. This bridges state-of-the-art NLP performance with human-understandable reasoning, satisfying both accuracy and transparency requirements. | Explainable BERT-based Classification combines the predictive power of fine-tuned BERT transformers for text classification with post-hoc or intrinsic explainability techniques — such as SHAP, LIME, attention analysis, or integrated gradients — to reveal which words or tokens drove each prediction. The result is a classifier that is both accurate and interpretable enough for high-stakes or auditable NLP applications. |
| ScholarGateSet de date ↗ |
|
|