Word Embedding Perturbation for Sentence Classification
Not on the map. Why?
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.
Key facts. Cited by 11 papers in the map (data through 14 Oct 2026). First posted on arXiv 22 Apr 2018.
Builds on
No reference list yet.
Built on by
Citing papers per year: 2021: 4; 2022: 3; 2023: 3; 2024: 1.
11 papers.
- 2021Certified Robustness to Text Adversarial Attacks by Randomized [MASK]cited by 57
- 2023Ultra-High-Resolution Detector Simulation with Intra-Event Aware GAN and Self-Supervised Relational Reasoningcited by 25
- 2022Improving the Adversarial Robustness of NLP Models by Information Bottleneckcited by 17
- 2023Incorporating Attribution Importance for Improving Faithfulness Metricscited by 14
- 2022BERTops: Studying BERT Representations under a Topological Lenscited by 5
- 2021Adversarial Attacks and Defenses for Social Network Text Processing Applications: Techniques, Challenges and Future Research Directionscited by 4
- 2023Effective Slogan Generation with Noise Perturbationcited by 2
- 2021NoiER: An Approach for Training more Reliable Fine-TunedDownstream Task Modelscited by 1
- 2021Sarcasm Detection in Twitter -- Performance Impact while using Data Augmentation: Word Embeddingscited by 0
- 2022ScaLA: Accelerating Adaptation of Pre-Trained Transformer-Based Language Models via Efficient Large-Batch Adversarial Noisecited by 0
- 2024Adversarial Attacks and Defense for Conversation Entailment Taskcited by 0
- 2024Adversarial Attacks and Defense for Conversation Entailment Task1 May 2024
- 2023Effective Slogan Generation with Noise Perturbation6 Oct 2023
- 2023Incorporating Attribution Importance for Improving Faithfulness Metrics17 May 2023
- 2023Ultra-High-Resolution Detector Simulation with Intra-Event Aware GAN and Self-Supervised Relational Reasoning7 Mar 2023
- 2022Improving the Adversarial Robustness of NLP Models by Information Bottleneck11 Jun 2022
- 2022BERTops: Studying BERT Representations under a Topological Lens2 May 2022
- 2022ScaLA: Accelerating Adaptation of Pre-Trained Transformer-Based Language Models via Efficient Large-Batch Adversarial Noise29 Jan 2022
- 2021Adversarial Attacks and Defenses for Social Network Text Processing Applications: Techniques, Challenges and Future Research Directions26 Oct 2021
- 2021NoiER: An Approach for Training more Reliable Fine-TunedDownstream Task Models29 Aug 2021
- 2021Sarcasm Detection in Twitter -- Performance Impact while using Data Augmentation: Word Embeddings23 Aug 2021
- 2021Certified Robustness to Text Adversarial Attacks by Randomized [MASK]8 May 2021