# Do Convolutional Networks need to be Deep for Text Classification ?

arXiv: https://arxiv.org/abs/1707.04108 · HTML: https://mlsanity.com/paper/1707.04108/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 13 Jul 2017.

## Built on by (most cited first, 11 of 11)

- [TIPCB: A Simple but Effective Part-based Convolutional Baseline for Text-based Person Search](https://mlsanity.com/paper/2105.11628/) (2021)
- [Towards Computationally Feasible Deep Active Learning](https://mlsanity.com/paper/2205.03598/) (2022)
- [An Explainable CNN Approach for Medical Codes Prediction from Clinical Text](https://mlsanity.com/paper/2101.11430/) (2021)
- [TextConvoNet:A Convolutional Neural Network based Architecture for Text Classification](https://mlsanity.com/paper/2203.05173/) (2022)
- [An Attention Ensemble Approach for Efficient Text Classification of Indian Languages](https://mlsanity.com/paper/2102.10275/) (2021)
- [Tackling COVID-19 Infodemic using Deep Learning](https://mlsanity.com/paper/2107.02012/) (2021)
- [Paradigm Shift in Language Modeling: Revisiting CNN for Modeling Sanskrit Originated Bengali and Hindi Language](https://mlsanity.com/paper/2110.13032/) (2021)
- [Contrastive Graph Multimodal Model for Text Classification in Videos](https://mlsanity.com/paper/2206.02343/) (2022)
- [KE-QI: A Knowledge Enhanced Article Quality Identification Dataset](https://mlsanity.com/paper/2206.07556/) (2022)
- [VKIE: The Application of Key Information Extraction on Video Text](https://mlsanity.com/paper/2310.11650/) (2023)
- [Employing Sentence Space Embedding for Classification of Data Stream from Fake News Domain](https://mlsanity.com/paper/2407.10807/) (2024)

## Abstract (arXiv)

We study in this work the importance of depth in convolutional models for text classification, either when character or word inputs are considered. We show on 5 standard text classification and sentiment analysis tasks that deep models indeed give better performances than shallow networks when the text input is represented as a sequence of characters. However, a simple shallow-and-wide network outperforms deep models such as DenseNet with word inputs. Our shallow word model further establishes new state-of-the-art performances on two datasets: Yelp Binary (95.9%) and Yelp Full (64.9%).