Xiang Lisa Li

Nelson Liu

Hi! I am a rising senior at Johns Hopkins University, majoring in Computer Science and Applied Mathmatics and Statistics.

I work on natural language processing, affiliated with the Center for Language and Speech Processing. I am advised by Prof. Jason Eisner. I work on structured prediction and syntax.

Last summer, I did research at Harvard NLP group, working with Prof. Sasha Rush. My project is about using discrete a latent variable model to aid interpretability and controllability of autoregressive neural network for data-to-text task.

Email: xli150 [at] jhu.edu

Links: [Full CV] [Twitter] [Github]


Publications

  • Specializing Word Embeddings (for Parsing) by Information Bottleneck
    Xiang Lisa Li and Jason Eisner
    In Conference on Empirical Methods in Natural Language Processing (EMNLP-IJCNLP), 2019.
    Best Paper Award at EMNLP-IJCNLP 2019
    [bib] [abstract] [appendix]

  • A Generative Model for Punctuation in Dependency Trees
    Xiang Lisa Li and Dingquan Wang and Jason Eisner.
    In Transactions of the Association for Computational Linguistics (TACL), 2019.
    [bib] [abstract] [arxiv]

Older publications on Medical Imaging:

Honors & Awards


Teaching Experience

  • (Fall 2019) CA @ Natural Language Processing (CS 520.465/665)
  • (Spring 2019) TA @ Introduction to Probability (AMS 553.420/620)
  • (Fall 2018) CA @ Natural Language Processing (CS 520.465/665)
  • (Fall 2018) TA @ Introduction to Probability (AMS 553.420/620)
  • (Spring 2017) TA @ Introduction to Probability (AMS 553.420/620)
  • (Fall 2017) TA @ Introduction to Probability (AMS 553.420/620)
  • Interestingly, a perpetual prob TA is switching to stats... Hope we can have fun in 430 :)