I will be joining the Toyota Technological Institute at Chicago (TTIC) as a Research Assistant Professor starting Fall 2024. If you are interested in working or collaborating with me on projects related to NLP or CL, please feel free to check out my prospective students page and consider reaching out!

About Me

Hi, I’m Zhewei, a computer science Ph.D. candidate at the University of Toronto advised by Professor Yang Xu in the Computational Lingusitics Group. Prior to Toronto, I received a M.S. degree from the Georgia Institute of Technology (working with Professor Jacob Eisenstein) and a B.S. degree from the University of Waterloo.

Research Interests

My research interests lie in natural language processing, computational linguistics, and computational social science. My work aims to bridge the gap between humans and natural language agents, giving AI agents the ability to process and produce language that is appropriate with respect to the communicative context. For example, I am interested in developing computational methods that allows an AI agent to:

  • Employ variations of language that are the most appropriate with respect to the communicative context.
  • Have the ability to generate and interpret language in creative ways (e.g., extending senses, coining new words).
  • Use language responsibly and adhere to human values.

To address these challenges, I employ computational methods from machine learning and cognitive science, with a particular interest in deep learning methods for natural language processing. At the same time, I am also interested in data-driven interdisciplinary research topics in computational linguistics and computational social science that offer insights to how humans use language.

Selected Publications

  • Zhewei Sun, Qian Hu, Rahul Gupta, Richard Zemel, and Yang Xu. “Toward Informal Language Processing: Knowledge of Slang in Large Language Models”. NAACL 2024 (To appear).

    [Paper] [GitHub]

  • Zhewei Sun and Yang Xu. “Tracing Semantic Variation in Slang”. EMNLP 2022.

    [Paper] [GitHub] [Slides] [Video] [BibTex]

  • Zhewei Sun, Richard Zemel, and Yang Xu. “A Computational Framework for Slang Generation”. TACL Vol. 9 (2021).

    [Paper] [GitHub] [Slides] [Video] [BibTex]

For a full list of my publications, see here.