About
I am a fourth-year Ph.D. student at Princeton University, advised by Prof. Danqi Chen.
I received an M.S. in Computer Science from
University of Illinois at Urbana-Champaign in 2019, advised by Prof. Tao Xie,
and a B.S. in Computer Science from Peking University in 2017.
I am fortunately supported by a J.P. Morgan PhD Fellowship.
I am interested in natural language processing. My long-term goal is to build efficient and robust systems that can understand human language. My recent research focused on (1) extracting structured infromation from unstructred text, (2) recalling factual knowledge from pre-trained language models, (3) analyzing generalization of dense retrieval models, and (4) developing new training objectives for training language models with memory augmentation.
Don't hesitate to reach out if you would like to chat about research (and life) with me!
*For UG students: I am happy to mentor a couple of undergradute students. If you are interested in my research topics and would like to do a research project with me, please fill out this form (from my lab) and email me!
Papers
(* indicates equal contribution)
-
Training Language Models with Memory Augmentation
Zexuan Zhong, Tao Lei, Danqi Chen
-
Recovering Private Text in Federated Learning of Language Models
Samyak Gupta*, Yangsibo Huang*, Zexuan Zhong, Tianyu Gao, Kai Li, Danqi Chen
-
Structured Pruning Learns Compact and Accurate Models
Mengzhou Xia, Zexuan Zhong, Danqi Chen
-
Should You Mask 15% in Masked Language Modeling?
Alexander Wettig*, Tianyu Gao*, Zexuan Zhong, Danqi Chen
arXiv 2202.08005
-
Simple Entity-Centric Questions Challenge Dense Retrievers
Christopher Sciavolino*, Zexuan Zhong*, Jinhyuk Lee, Danqi Chen
-
A Frustratingly Easy Approach for Entity and Relation Extraction
Zexuan Zhong, Danqi Chen
-
Factual Probing Is [MASK]: Learning vs. Learning to Recall
Zexuan Zhong*, Dan Friedman*, Danqi Chen
-
Robustra: Training Provable Robust Neural Networks over Reference Adversarial Space
Linyi Li*, Zexuan Zhong*, Bo Li, Tao Xie
-
Learning Food Quality and Safety using Wireless Stickers
Unsoo Ha, Yunfei Ma, Zexuan Zhong, Tzu-Ming Hsu, Fadel Adib
-
SemRegex: A Semantics-Based Approach for Generating Regular Expressions from Natural Language Specifications
Zexuan Zhong, Jiaqi Guo, Wei Yang, Jian Peng, Tao Xie, Jian-Guang Lou, Ting Liu, Dongmei Zhang
-
CoLink: An Unsupervised Framework for User Identity Linkage
Zexuan Zhong, Yong Cao, Mu Guo, Zaiqing Nie
-
Generating Regular Expressions from Natural Language Specifications: Are We There Yet?
Zexuan Zhong, Jiaqi Guo, Wei Yang, Tao Xie, Jian-Guang Lou, Ting Liu, Dongmei Zhang
-
MULDEF: Multi-model-based Defense Against Adversarial Examples for Neural Networks
Siwakorn Srisakaokul, Zexuan Zhong, Yuhao Zhang, Wei Yang, Tao Xie
arXiv 1809.00065
Education
-
2019.9 - present, Princeton University
Ph.D. in Computer Science
-
2017.8 - 2019.5, University of Illinois at Urbana-Champaign
M.S. in Computer Science
-
2013.9 - 2017.7, Peking University
B.S. in Computer Science and Technology
Experience
-
2017.8 - 2019.5, Research Assistant, University of Illinois at Urbana-Champaign
Advisor: Prof. Tao Xie
-
2018.5 - 2018.8, Visiting Research Assistant, MIT Media Lab
Advisor: Prof. Fadel Adib
-
2016.7 - 2017.5, Research Intern, Microsoft Research Asia
Mentors: Dr. Zaiqing Nie and Dr. Yong Cao
-
2015.11 - 2016.5, Research Assistant, Peking University
Advisor: Prof. Yingfei Xiong
Programming Contests
-
Finalist, ACM-ICPC World Final, 2019
-
Gold Medal, ACM-ICPC Mid-Central USA Regionals Chicago site, 2018
-
Gold Medal, ACM-ICPC Mid-Central USA Regionals Chicago site, 2017
-
Gold Medal, ACM-ICPC Asia Regionals Changchun site, 2013
-
Gold Medal, China National Olympiad in Informatics, 2012
Contact
35 Olden St, Princeton, NJ 08540, USA
Email: zzhong@princeton.edu