From explainable to interpretable deep learning for natural language processing in healthcare: How far from reality?

From explainable to interpretable deep learning for natural language processing in healthcare: How far from reality?
Computational and Structural Biotechnology Journal; by Guangming Huang, Yingya Li, Shoaib Jameel, Yunfei Long, Giorgos Papanastasiou;12/24
Deep learning (DL) has substantially enhanced natural language processing (NLP) in healthcare research. However, the increasing complexity of DL-based NLP necessitates transparent model interpretability, or at least explainability, for reliable decision-making. This work presents a thorough scoping review of explainable and interpretable DL in healthcare NLP.