To be Robust and to be Fair: Aligning Fairness with Robustness

no code implementations • 31 Mar 2023 • Junyi Chai, Xiaoqian Wang

both fairness and accuracy?

Adversarial Attack Fairness

Fairness without Demographics through Knowledge Distillation

1 code implementation • NIPS 2022 • Junyi Chai, Taeuk Jang ~Taeuk_Jang1, Xiaoqian Wang

Most of existing work on fairness assumes available demographic information in the training set.

Fairness Knowledge Distillation

FAST: Improving Controllability for Text Generation with Feedback Aware Self-Training

no code implementations • 6 Oct 2022 • Junyi Chai, Reid Pryzant, Victor Ye Dong, Konstantin Golobokov, Chenguang Zhu, Yi Liu

Controllable text generation systems often leverage control codes to direct various properties of the output like style and length.

Attribute Causal Inference +2

DeepGen: Diverse Search Ad Generation and Real-Time Customization

no code implementations • 6 Aug 2022 • Konstantin Golobokov, Junyi Chai, Victor Ye Dong, Mandy Gu, Bingyu Chi, Jie Cao, Yulan Yan, Yi Liu

In addition, our system creates a customized ad in real-time in response to the user's search query, therefore highlighting different aspects of the same product based on what the user is looking for.

Text Generation

Automatic Construction of Enterprise Knowledge Base

no code implementations • EMNLP (ACL) 2021 • Junyi Chai, Yujie He, Homa Hashemi, Bing Li, Daraksha Parveen, Ranganath Kondapally, Wenjin Xu

In this paper, we present an automatic knowledge base construction system from large scale enterprise documents with minimal efforts of human intervention.