# Learning Robust Representations of Text

arXiv: https://arxiv.org/abs/1609.06082 · HTML: https://mlsanity.com/paper/1609.06082/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 20 Sep 2016.

## Built on by (most cited first, 6 of 6)

- [Analyzing the Role of Semantic Representations in the Era of Large Language Models](https://mlsanity.com/paper/2405.01502/) (2024)
- [Identifying Adversarial Attacks on Text Classifiers](https://mlsanity.com/paper/2201.08555/) (2022)
- [Misspellings in Natural Language Processing: A survey](https://mlsanity.com/paper/2501.16836/) (2025)
- [Detecting Textual Adversarial Examples Based on Distributional Characteristics of Data Representations](https://mlsanity.com/paper/2204.13853/) (2022)
- [An Introduction to Robust Graph Convolutional Networks](https://mlsanity.com/paper/2103.14807/) (2021)
- [What Learned Representations and Influence Functions Can Tell Us About Adversarial Examples](https://mlsanity.com/paper/2309.10916/) (2023)

## Abstract (arXiv)

Deep neural networks have achieved remarkable results across many language processing tasks, however these methods are highly sensitive to noise and adversarial attacks. We present a regularization based method for limiting network sensitivity to its inputs, inspired by ideas from computer vision, thus learning models that are more robust. Empirical evaluation over a range of sentiment datasets with a convolutional neural network shows that, compared to a baseline model and the dropout method, our method achieves superior performance over noisy inputs and out-of-domain data.