Dynamically Disentangling Social Bias from Task-Oriented Representations with Adversarial Attack.
Liwen WangYuanmeng YanKeqing HeYanan WuWeiran XuPublished in: NAACL-HLT (2021)
Keyphrases
- social networks
- social interaction
- neural network
- multi agent
- countermeasures
- social networking
- denial of service attacks
- social learning
- secret key
- representation scheme
- description language
- symbolic representation
- higher level
- social media
- dialogue system
- natural language
- social behavior
- genetic algorithm
- social context
- machine learning