# Understanding Convolutional Neural Networks for Text Classification

arXiv: https://arxiv.org/abs/1809.08037 · HTML: https://mlsanity.com/paper/1809.08037/

## Key facts

- Cited by 36 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 21 Sep 2018.

## Built on by (most cited first, 30 of 36)

- [Neurons in Large Language Models: Dead, N-gram, Positional](https://mlsanity.com/paper/2309.04827/) (2023)
- [SelfExplain: A Self-Explaining Architecture for Neural Text Classifiers](https://mlsanity.com/paper/2103.12279/) (2021)
- [DecompX: Explaining Transformers Decisions by Propagating Token Decomposition](https://mlsanity.com/paper/2306.02873/) (2023)
- [Model Explainability in Deep Learning Based Natural Language Processing](https://mlsanity.com/paper/2106.07410/) (2021)
- [Explainable AI for Bioinformatics: Methods, Tools, and Applications](https://mlsanity.com/paper/2212.13261/) (2022)
- [Dissecting Generation Modes for Abstractive Summarization Models via Ablation and Attribution](https://mlsanity.com/paper/2106.01518/) (2021)
- [ShufText: A Simple Black Box Approach to Evaluate the Fragility of Text Classification Models](https://mlsanity.com/paper/2102.00238/) (2021)
- [Self-interpretable Convolutional Neural Networks for Text Classification](https://mlsanity.com/paper/2105.08589/) (2021)
- [TextConvoNet:A Convolutional Neural Network based Architecture for Text Classification](https://mlsanity.com/paper/2203.05173/) (2022)
- [Learning to Select Prototypical Parts for Interpretable Sequential Data Modeling](https://mlsanity.com/paper/2212.03396/) (2022)
- [Continual Graph Convolutional Network for Text Classification](https://mlsanity.com/paper/2304.04152/) (2023)
- [LioNets: A Neural-Specific Local Interpretation Technique Exploiting Penultimate Layer Information](https://mlsanity.com/paper/2104.06057/) (2021)
- [StyLEx: Explaining Style Using Human Lexical Annotations](https://mlsanity.com/paper/2210.07469/) (2022)
- [Extracting Lexical Features from Dialects via Interpretable Dialect Classifiers](https://mlsanity.com/paper/2402.17914/) (2024)
- [DepressionX: Knowledge Infused Residual Attention for Explainable Depression Severity Assessment](https://mlsanity.com/paper/2501.14985/) (2025)
- [DEMASQ: Unmasking the ChatGPT Wordsmith](https://mlsanity.com/paper/2311.05019/) (2023)
- [Advancing Interpretability in Text Classification through Prototype Learning](https://mlsanity.com/paper/2410.17546/) (2024)
- [Pegasus: A Universal Framework for Scalable Deep Learning Inference on the Dataplane](https://mlsanity.com/paper/2506.05779/) (2025)
- [Data-driven Smart Ponzi Scheme Detection](https://mlsanity.com/paper/2108.09305/) (2021)
- [WrapperFL: A Model Agnostic Plug-in for Industrial Federated Learning](https://mlsanity.com/paper/2206.10407/) (2022)
- [Towards a Game-theoretic Understanding of Explanation-based Membership Inference Attacks](https://mlsanity.com/paper/2404.07139/) (2024)
- [Explainability of machine learning approaches in forensic linguistics: a case study in geolinguistic authorship profiling](https://mlsanity.com/paper/2404.18510/) (2024)
- [Enhancing Suicide Risk Detection on Social Media through Semi-Supervised Deep Label Smoothing](https://mlsanity.com/paper/2405.05795/) (2024)
- [Classifying several dialectal Nawatl varieties](https://mlsanity.com/paper/2601.02303/) (2026)
- [Structural block driven - enhanced convolutional neural representation for relation extraction](https://mlsanity.com/paper/2103.11356/) (2021)
- [Robustness Tests of NLP Machine Learning Models: Search and Semantically Replace](https://mlsanity.com/paper/2104.09978/) (2021)
- [Understanding Information Spreading Mechanisms During COVID-19 Pandemic by Analyzing the Impact of Tweet Text and User Features for Retweet Prediction](https://mlsanity.com/paper/2106.07344/) (2021)
- [Unsupervised Technique To Conversational Machine Reading](https://mlsanity.com/paper/2106.15247/) (2021)
- [A Game-theoretic Understanding of Repeated Explanations in ML Models](https://mlsanity.com/paper/2202.02659/) (2022)
- [Multidimensional Perceptron for Efficient and Explainable Long Text Classification](https://mlsanity.com/paper/2304.01638/) (2023)

## Abstract (arXiv)

We present an analysis into the inner workings of Convolutional Neural Networks (CNNs) for processing text. CNNs used for computer vision can be interpreted by projecting filters into image space, but for discrete sequence inputs CNNs remain a mystery. We aim to understand the method by which the networks process and classify text. We examine common hypotheses to this problem: that filters, accompanied by global max-pooling, serve as ngram detectors. We show that filters may capture several different semantic classes of ngrams by using different activation patterns, and that global max-pooling induces behavior which separates important ngrams from the rest. Finally, we show practical use cases derived from our findings in the form of model interpretability (explaining a trained model by deriving a concrete identity for each filter, bridging the gap between visualization tools in vision tasks and NLP) and prediction interpretability (explaining predictions). Code implementation is available online at github.com/sayaendo/interpreting-cnn-for-text.