113941 -

: Common architectures include Convolutional Neural Networks (CNNs) and Recurrent Neural Networks (RNNs) used to model complex relationships in text data.

: The paper introduces Confident Itemsets Explanation (CIE) , a model-agnostic method that identifies sets of features (words or tokens) that strongly influence a model's prediction. 113941

Post-hoc explanation of black-box classifiers using confident itemsets 113941

: These models often require large datasets and can be sensitive to "adversarial noise" (small character-level changes that fool the AI). 113941