Confronta i metodi
Esamina i metodi selezionati fianco a fianco; le righe che differiscono sono evidenziate.
| Embeddings di Frase Spiegabili× | Rete Neurale Ricorrente Spiegabile× | |
|---|---|---|
| Campo | Apprendimento profondo | Apprendimento profondo |
| Famiglia | Machine learning | Machine learning |
| Anno di origine≠ | 2016–2018 | 2017–2020 |
| Ideatore≠ | Conneau et al.; Ribeiro et al. (probing + LIME frameworks) | Arrived via XAI literature (Arrieta et al., Lundberg & Lee, and attention-based RNN work) |
| Tipo≠ | Post-hoc interpretability applied to sentence encoders | Interpretability framework applied to sequence models |
| Fonte seminale≠ | Conneau, A., Kruszewski, G., Lample, G., Barrault, L., & Baroni, M. (2018). What you can cram into a single $\vec{v}$ector: Probing sentence embeddings for linguistic properties. In Proceedings of ACL 2018, pp. 2126–2136. link ↗ | 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. DOI ↗ |
| Alias | interpretable sentence representations, XAI sentence embeddings, probing sentence embeddings, explainable sentence vectors | Explainable RNN, Interpretable RNN, XAI-RNN, Transparent Recurrent Neural Network |
| Correlati≠ | 6 | 5 |
| Sintesi≠ | Explainable sentence embeddings combine dense sentence representation learning with post-hoc or intrinsic interpretability tools — such as probing classifiers, LIME, SHAP, or attention attribution — to reveal what linguistic and semantic information is encoded in a sentence vector and why a downstream model makes a given prediction. The goal is to retain the representational power of modern encoders while making their behavior auditable. | 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. |
| ScholarGateInsieme di dati ↗ |
|
|