Comparer des méthodes

	Classification basée sur BERT explicable	Réseau de neurones récurrent explicable
Domaine	Apprentissage profond	Apprentissage profond
Famille	Machine learning	Machine learning
Année d'origine	2019–2020	2017–2020
Auteur d'origine	Devlin et al. (BERT); explainability methods by Lundberg & Lee (SHAP), Ribeiro et al. (LIME), Sundararajan et al. (Integrated Gradients)	Arrived via XAI literature (Arrieta et al., Lundberg & Lee, and attention-based RNN work)
Type	Pre-trained transformer classifier with post-hoc or intrinsic explainability	Interpretability framework applied to sequence models
Source fondatrice	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.	Arrieta, A. B., Diaz-Rodriguez, N., Del Ser, J., Bennetot, A., Tabik, S., Barbado, A., Garcia, S., Gil-Lopez, S., Molina, D., Benjamins, R., Chatila, R., & Herrera, F. (2020). Explainable Artificial Intelligence (XAI): Concepts, taxonomies, opportunities and challenges toward responsible AI. Information Fusion, 58, 82–115.
Alias	XAI-BERT, interpretable BERT classifier, BERT with post-hoc explanation, transparent BERT classification	Explainable RNN, Interpretable RNN, XAI-RNN, Transparent Recurrent Neural Network
Apparentées	6	5
Résumé	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.	An Explainable Recurrent Neural Network (XAI-RNN) pairs a standard RNN architecture with a post-hoc or intrinsic interpretability method — such as SHAP, LIME, integrated gradients, or attention visualization — to reveal which input time steps or tokens most influence the model's sequential predictions, without sacrificing predictive accuracy.