Interpretable-by-Design Text Understanding with Iteratively Generated Concept Bottleneck

arXiv:2310.19660v2 Announce Type: replace
Abstract: Black-box deep neural networks excel in text classification, yet their application in high-stakes domains is hindered by their lack of interpretability. To address this, we propose Text Bottleneck Models (TBM), an intrinsically interpretable text classification framework that offers both global and local explanations. Rather than directly predicting the output label, TBM predicts categorical values for a sparse set of salient concepts and uses a linear layer over those concept values to produce the final prediction. …

abstract application arxiv box classification concept cs.cl design domains excel framework generated global interpretability networks neural networks text text classification text understanding type understanding