Office: USC PHE #332
Email: jieyuz [at] usc [dot] edu
Last Update: 10/30/2023
Jieyu Zhao 赵洁玉
Gabilan Assistant Professor
Thomas Lord Department of Computer Science, USC
Jieyu Zhao is an Assistant Professor of Computer Science Department at University of Southern California. Prior to that, she was an NSF Computing Innovation Fellow at University of Maryland, College Park, working with Prof. Hal Daumé III. Jieyu received her Ph.D. from Computer Science Department, UCLA, where she was advised by Prof. Kai-Wei Chang. Her research interest lies in fairness of ML/NLP models. Her paper got the EMNLP Best Long Paper Award (2017). She was one of the recipients of 2020 Microsoft PhD Fellowship and has been selected to participate in 2021 Rising Stars in EECS workshop. Her research has been covered by news media such as Wired, The Daily Mail and so on. She was invited by UN-WOMEN Beijing on a panel discussion about gender equality and social responsibility.
I'm actively looking for strong and motivated students (1-2 PhDs for 2024 Fall). We welcome applicants from diverse backgrounds. If you are interested in my research, please fill in this form.
🐾 Research
I am broadly interested in research about how to get machines to understand and respond to human languages (natural language processing & machine learning). A few questions that drive my recent research are:
- how can we get models to efficiently learn knowledge?
- how can we reduce potential harms learned by the model?
- how can we advance better models and humans collaborations?
📰 Recent News
- [09/2023] We got two papers accepted at EMNLP 2023 and one accepted to WiNLP workshop. Congrats to the collaborators! Check Publications for more!
- [09/2023] Our TACO🌮 paper has been accepted to NeurIPS. Check Publications for more!
- [08/16/2023] I started my job at USC! Go Trojans!
- [06/2023] One paper was accepted to IMCL AdvML-Frontiers workshop!
🗞️️ More News
- [10/2022] One paper was accepted at EMNLP 2022 Findings. Check it out!
- [10/2022] We got a paper accepted at AACL. Check it out!
- [10/2022] We will do a "Trustworthy and Responsible AI" tutorial at AAAI 2023. Stay tuned!
- [06/2022] I serve as an AAAI workflow chair.
- [04/2022] I will join USC CS as an Assistant Professor in 2023 Fall! 🥳 Let me know if you are interested in working with me! 🎉
- [01/2022] I'm here at UMD now. Feel free to drop by or send me an email for discussions!
Publications (selected)
A Rose by Any Other Name would not Smell as Sweet: Social Bias in Name Mistranslations
Sandra Sandoval, Jieyu Zhao, Marine Carpuat, and Hal Daume III. EMNLP 2023.Are Personalized Stochastic Parrots More Dangerous? Evaluating Persona Biases in Dialogue Systems
Yixin Wan, Jieyu Zhao, Aman Chadha, Nanyun Peng, and Kai-Wei Chang. EMNLP-Finding, 2023.Mind What You Measure For: A Study on Reliability of Prompt-Based Bias Measurement
Ruyuan Zuo, and Jieyu Zhao. WiNLP 2023.- TACO: Temporal Latent Action-Driven Contrastive Loss For Visual Reinforcement Learning
Ruijie Zheng, Xiyao Wang, Yanchao Sun, Shuang Ma, Jieyu Zhao, Huazhe Xu, Hal Daume, Furong Huang. NeurIPS, 2023.
SODAPOP: Open-Ended Discovery of Social Biases in Social Commonsense Reasoning Models
Haozhe An, Zongxia Li, Jieyu Zhao, Rachel Rudinger. EACL 2023.Investigating Ensemble Methods for Model Robustness Improvement of Text Classifiers
Jieyu Zhao, Xuezhi Wang, Yao Qin, Jilin Chen, Kai-Wei Chang. EMNLP Findings, 2022.-
Ethical-Advice Taker: Do Language Models Understand Natural Language Interventions?
Jieyu Zhao, Daniel Khashabi, Tushar Khot, Ashish Sabharwal, and Kai-Wei Chang. ACL Findings, 2021. -
Double Perturbation: On the Robustness of Robustness and Counterfactual Bias Evaluation
Chong Zhang, Jieyu Zhao, Huan Zhang, Kai-Wei Chang, and Cho-Jui Hsieh. NAACL 2021. - Gender Bias in Multilingual Embeddings and Cross-Lingual Transfer
Jieyu Zhao, Subhabrata Mukherjee, Saghar Hosseini, Kai-Wei Chang, Ahmed Hassan Awadallah.
Conference of the Association for Computational Linguistics. ACL 2020.
- Mitigating Gender Bias Amplification in Distribution by Posterior Regularization
Shengyu Jia*, Tao Meng*, Jieyu Zhao, Kai-Wei Chang.
Conference of the Association for Computational Linguistics. ACL 2020.
- Balanced Datasets Are Not Enough: Estimating and Mitigating
Gender Bias in Deep Image Representations
Tianlu Wang, Jieyu Zhao, Mark Yatskar, Kai-Wei Chang, Vicente Ordonez.
International Conference on Computer Vision. ICCV 2019.
- Gender Bias in Coreference Resolution: Evaluation and
Debiasing Methods [code] [podcast]
Jieyu Zhao, Tianlu Wang, Mark Yatskar, Vicente Ordonez, Kai-Wei Chang.
North American Chapter of the Association for Computational Linguistics. NAACL 2018.
- Men Also Like Shopping: Reducing Gender Bias Amplification
using Corpus-level Constraints [code], [slides]
Jieyu Zhao, Tianlu Wang, Mark Yatskar, Vicente Ordonez, Kai-Wei Chang.
Conference on Empirical Methods in Natural Language Processing. EMNLP 2017. (Best Long Paper Award)
Press: Wired: Machines Taught By Photos Learn a Sexist View of Women
Talks
- Tutorial: Trustworthy and Responsible AI. AAAI 2023.
- Detect and mitigate bias in NLP. AKBC KG-BIAS work shop, 2020.
Education / Experience
- Postdoc, University of Maryland, College Park. 2022.01 - 2023.06
- Ph.D., University of California, Los Angeles. 2017.9 - 2021.12
- Google Research Intern, NYC. 2021.06 - 2021.09
- AI2 Research Intern, Seattle. 2020.09 - 2020.12
- Microsoft Research Intern, Redmond. 2020.06 - 2020.09
- Microsoft Research Intern, Redmond. 2019.06 - 2019.09
Awards (selected)
- CI Fellowship, 2021
- EECS Rising Star, 2021
- Microsoft PhD Fellowship, 2020
- SoCalNLP Symposium Best Poster Award, 2018
- UCLA Graduate Division Fellowships, 2017
- EMNLP 2017 Best Long Paper Award, 2017
- Outstanding Graduate of Beijing City, 2016