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)
  1. Training Language Models with Memory Augmentation
    Zexuan Zhong, Tao Lei, Danqi Chen
    Download: [PDF] [Code]
  2. Recovering Private Text in Federated Learning of Language Models
    Samyak Gupta*, Yangsibo Huang*, Zexuan Zhong, Tianyu Gao, Kai Li, Danqi Chen
    Download: [PDF] [Code]
  3. Structured Pruning Learns Compact and Accurate Models
    Mengzhou Xia, Zexuan Zhong, Danqi Chen
    Download: [PDF] [Code]
  4. Should You Mask 15% in Masked Language Modeling?
    Alexander Wettig*, Tianyu Gao*, Zexuan Zhong, Danqi Chen
    arXiv 2202.08005
    Download: [PDF] [Code]
  5. Simple Entity-Centric Questions Challenge Dense Retrievers
    Christopher Sciavolino*, Zexuan Zhong*, Jinhyuk Lee, Danqi Chen
    Download: [PDF] [Code]
  6. A Frustratingly Easy Approach for Entity and Relation Extraction
    Zexuan Zhong, Danqi Chen
    Download: [PDF] [Code]
  7. Factual Probing Is [MASK]: Learning vs. Learning to Recall
    Zexuan Zhong*, Dan Friedman*, Danqi Chen
    Download: [PDF] [Code]
  8. Robustra: Training Provable Robust Neural Networks over Reference Adversarial Space
    Linyi Li*, Zexuan Zhong*, Bo Li, Tao Xie
    Download: [PDF]
  9. Learning Food Quality and Safety using Wireless Stickers
    Unsoo Ha, Yunfei Ma, Zexuan Zhong, Tzu-Ming Hsu, Fadel Adib
    Download: [PDF]
  10. 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
    Download: [PDF]
  11. CoLink: An Unsupervised Framework for User Identity Linkage
    Zexuan Zhong, Yong Cao, Mu Guo, Zaiqing Nie
    Download: [PDF]
  12. 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
    Download: [PDF]
  13. MULDEF: Multi-model-based Defense Against Adversarial Examples for Neural Networks
    Siwakorn Srisakaokul, Zexuan Zhong, Yuhao Zhang, Wei Yang, Tao Xie
    arXiv 1809.00065
    Download: [PDF]

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

Honors

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