Hangfeng He

Sample logotype

Ph.D. Student

Computer and Information Science

University of Pennsylvania

Email: hangfeng@seas.upenn.edu

Office: 456C, 3401 Walnut



I am a fifth-year Ph.D. student, working with Dan Roth and Weijie Su, in the Department of Computer and Information Science at the University of Pennsylvania. My research interests include machine learning and natural language processing, with a focus on moving beyond scale-driven learning. Specifically, I work on incidental supervision for natural language understanding, interpretability of deep neural networks, reasoning in natural language, and structured data modeling.

Before that, I received B.S. in Computer Science at Peking University in 2017, where I worked with Tingting Jiang. In summer 2016, I worked as a research intern with Bonnie Webber at the University of Edinburgh.

I'm on the 2021-2022 job market, looking for tenure-track faculty positions.

Application Materials: [Research Statement] [Teaching Statement] [Diversity Statement]

[Google Scholar] [CV]


  1. Weighted Training for Cross-Task Learning
    Shuxiao Chen, Koby Crammer, Hangfeng He, Dan Roth, and Weijie Su (alphabetical order)
    In ICLR 2022. [pdf] [code]
  2. Exploring Deep Neural Networks via Layer-Peeled Model: Minority Collapse in Imbalanced Training
    Cong Fang, Hangfeng He, Qi Long, and Weijie Su (alphabetical order)
    In PNAS 2021. [pdf] [code]
  3. Foreseeing the Benefits of Incidental Supervision
    Hangfeng He, Mingyuan Zhang, Qiang Ning, and Dan Roth
    In EMNLP 2021. [pdf] [code]
  4. Toward Better Generalization Bounds with Locally Elastic Stability
    Zhun Deng, Hangfeng He, and Weijie Su
    In ICML 2021. [pdf]
  5. QANom: Question-Answer driven SRL for Nominalizations
    Ayal Klein, Jonathan Mamou, Valentina Pyatkin, Daniela Brook Weiss, Hangfeng He, Dan Roth, Luke Zettlemoyer, and Ido Dagan
    In COLING 2020. [pdf]
  6. Label-Aware Neural Tangent Kernel: Toward Better Generalization and Local Elasticity
    Shuxiao Chen, Hangfeng He, and Weijie Su (alphabetical order)
    In NeurIPS 2020. [pdf] [code]
  7. Towards Understanding the Dynamics of the First-Order Adversaries
    Zhun Deng, Hangfeng He, Jiaoyang Huang, and Weijie Su
    In ICML 2020. [pdf]
  8. QuASE: Question-Answer Driven Sentence Encoding
    Hangfeng He, Qiang Ning, and Dan Roth
    In ACL 2020. [pdf] [code] [demo]
  9. Understanding Spatial Relations through Multiple Modalities
    Soham Dan, Hangfeng He, and Dan Roth
    In LREC 2020 (short papers). [pdf]
  10. The Local Elasticity of Neural Networks
    Hangfeng He and Weijie Su
    In ICLR 2020. [pdf] [code]
  11. Partial or Complete, That’s The Question
    Qiang Ning, Hangfeng He, Chuchu Fan, and Dan Roth
    In NAACL-HLT 2019. [pdf]
  12. Cross-Domain and Semi-Supervised Named Entity Recognition in Chinese Social Media: A Unified Model
    Jingjing Xu, Hangfeng He, Xu Sun, Xuancheng Ren, and Sujian Li
    In TASLP 2018. [pdf]
  13. Detecting negation scope is easy, except when it isn’t
    Federico Fancellu, Adam Lopez, Bonnie Webber, and Hangfeng He
    In EACL 2017 (short papers). [pdf]
  14. F-Score Driven Max Margin Neural Network for Named Entity Recognition in Chinese Social Media
    Hangfeng He and Xu Sun
    In EACL 2017 (short papers). [pdf]
  15. A Unified Model for Cross-Domain and Semi-Supervised Named Entity Recognition in Chinese Social Media
    Hangfeng He and Xu Sun
    In AAAI 2017. [pdf]


  1. Robust Learning Rate Selection for Stochastic Optimization via Splitting Diagnostic
    Matteo Sordello, Hangfeng He, and Weijie Su
    In Arxiv 2019. [pdf]

Teaching Experience

Professional Service

Honors and Awards