# Self-interpretable Convolutional Neural Networks for Text Classification

arXiv: https://arxiv.org/abs/2105.08589 · HTML: https://mlsanity.com/paper/2105.08589/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 9 of its 11 references that are in the map.
- First posted on arXiv 18 May 2021.

## Builds on (most cited first, 9 of 9)

- [A Unified Approach to Interpreting Model Predictions](https://mlsanity.com/paper/1705.07874/) (2017)
- ["Why Should I Trust You?": Explaining the Predictions of Any Classifier](https://mlsanity.com/paper/1602.04938/) (2016)
- [Axiomatic Attribution for Deep Networks](https://mlsanity.com/paper/1703.01365/) (2017)
- [Convolutional Neural Networks for Sentence Classification](https://mlsanity.com/paper/1408.5882/) (2014)
- [Consistent Individualized Feature Attribution for Tree Ensembles](https://mlsanity.com/paper/1802.03888/) (2018)
- ["What is Relevant in a Text Document?": An Interpretable Machine Learning Approach](https://mlsanity.com/paper/1612.07843/) (2016)
- [Understanding Convolutional Neural Networks for Text Classification](https://mlsanity.com/paper/1809.08037/) (2018)
- [Unwrapping The Black Box of Deep ReLU Networks: Interpretability, Diagnostics, and Simplification](https://mlsanity.com/paper/2011.04041/) (2020)
- [SHAP values for Explaining CNN-based Text Classification Models](https://mlsanity.com/paper/2008.11825/) (2020)

## Built on by (most cited first, 5 of 5)

- [Model Explainability in Deep Learning Based Natural Language Processing](https://mlsanity.com/paper/2106.07410/) (2021)
- [Traversing the Local Polytopes of ReLU Neural Networks: A Unified Approach for Network Verification](https://mlsanity.com/paper/2111.08922/) (2021)
- [On marginal feature attributions of tree-based models](https://mlsanity.com/paper/2302.08434/) (2023)
- [Advances in Pre-trained Language Models for Domain-Specific Text Classification: A Systematic Review](https://mlsanity.com/paper/2510.17892/) (2025)
- [Explainable Product Classification for Customs](https://mlsanity.com/paper/2311.10922/) (2023)

## Abstract (arXiv)

Deep learning models for natural language processing (NLP) are inherently complex and often viewed as black box in nature. This paper develops an approach for interpreting convolutional neural networks for text classification problems by exploiting the local-linear models inherent in ReLU-DNNs. The CNN model combines the word embedding through convolutional layers, filters them using max-pooling, and optimizes using a ReLU-DNN for classification. To get an overall self-interpretable model, the system of local linear models from the ReLU DNN are mapped back through the max-pool filter to the appropriate n-grams. Our results on experimental datasets demonstrate that our proposed technique produce parsimonious models that are self-interpretable and have comparable performance with respect to a more complex CNN model. We also study the impact of the complexity of the convolutional layers and the classification layers on the model performance.