Towards Trustworthy NLP: An Adversarial Robustness Enhancement Based on Perplexity Difference.
Zhaocheng GeHanping HuTengfei ZhaoPublished in: ECAI (2023)
Keyphrases
- natural language processing
- image processing
- natural language
- language model
- image enhancement
- topic models
- question answering
- text analysis
- high robustness
- semantic analysis
- generative model
- objective function
- word sense disambiguation
- case study
- genetic algorithm
- language processing
- convex functions
- neural network