# Word Embedding Perturbation for Sentence Classification

arXiv: https://arxiv.org/abs/1804.08166 · HTML: https://mlsanity.com/paper/1804.08166/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 22 Apr 2018.

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

- [Certified Robustness to Text Adversarial Attacks by Randomized [MASK]](https://mlsanity.com/paper/2105.03743/) (2021)
- [Ultra-High-Resolution Detector Simulation with Intra-Event Aware GAN and Self-Supervised Relational Reasoning](https://mlsanity.com/paper/2303.08046/) (2023)
- [Improving the Adversarial Robustness of NLP Models by Information Bottleneck](https://mlsanity.com/paper/2206.05511/) (2022)
- [Incorporating Attribution Importance for Improving Faithfulness Metrics](https://mlsanity.com/paper/2305.10496/) (2023)
- [BERTops: Studying BERT Representations under a Topological Lens](https://mlsanity.com/paper/2205.00953/) (2022)
- [Adversarial Attacks and Defenses for Social Network Text Processing Applications: Techniques, Challenges and Future Research Directions](https://mlsanity.com/paper/2110.13980/) (2021)
- [Effective Slogan Generation with Noise Perturbation](https://mlsanity.com/paper/2310.04472/) (2023)
- [NoiER: An Approach for Training more Reliable Fine-TunedDownstream Task Models](https://mlsanity.com/paper/2110.02054/) (2021)
- [Sarcasm Detection in Twitter -- Performance Impact while using Data Augmentation: Word Embeddings](https://mlsanity.com/paper/2108.09924/) (2021)
- [ScaLA: Accelerating Adaptation of Pre-Trained Transformer-Based Language Models via Efficient Large-Batch Adversarial Noise](https://mlsanity.com/paper/2201.12469/) (2022)
- [Adversarial Attacks and Defense for Conversation Entailment Task](https://mlsanity.com/paper/2405.00289/) (2024)

## Abstract (arXiv)

In this technique report, we aim to mitigate the overfitting problem of natural language by applying data augmentation methods. Specifically, we attempt several types of noise to perturb the input word embedding, such as Gaussian noise, Bernoulli noise, and adversarial noise, etc. We also apply several constraints on different types of noise. By implementing these proposed data augmentation methods, the baseline models can gain improvements on several sentence classification tasks.