PRIS-NLP Group
PRIS-NLP Group
Home
Reseach Direction
People
Papers
Projects
Patents
Blogs
Careers
Contact
Light
Dark
Automatic
English
English
中文 (简体)
"Debias"
Dynamically Disentangling Social Bias from Task-Oriented Representations with Adversarial Attack
Representation learning is widely used in NLP for a vast range of tasks. However, representations derived from text corpora often reflect social biases. This phenomenon is pervasive and consistent across different neural models, causing serious …
Cite
×