I conduct research in natural language processing, specifically syntactic parsing, grammar induction, and multilingual modeling. More broadly, I am interested in designing models that can automatically discover linguistic structure.
I also work on developing secure distributed algorithms using ideas from cryptography and coding theory. In the past, I worked on computational Magnetic Resonance Imaging.
[May 2020] I had a great time discussing multilingual models with Matt Gardner and Pradeep Dasigi as a guest on the NLP Highlights podcast! You can find the episode here.
[April 2020] I presented Multilingual Alignment of Contextual Word Representations at ICLR 2020! You can find the video and poster here.
Multilingual Alignment of Contextual Word Representations
Steven Cao, Nikita Kitaev, Dan Klein
International Conference on Learning Representations (ICLR), 2020.
Multilingual Constituency Parsing with Self-Attention and Pre-Training
Nikita Kitaev, Steven Cao, Dan Klein
Association for Computational Linguistics (ACL), 2019 (Oral).
Learning-based Single-step Quantitative Susceptibility Mapping Reconstruction Without Brain Extraction
Hongjiang Wei, Steven Cao, Yuyao Zhang, Xiaojun Guan, Fuhua Yan, Kristen Yeom, Chunlei Liu
Imaging Diamagnetic Susceptibility of Collagen in Hepatic Fibrosis Using Susceptibility Tensor Imaging
Hongjiang Wei, Kyle Decker, Hien Nguyen, Steven Cao, Tsung‐Yuan Tsai, Cynthia Dianne Guy, Mustafa Bashir, Chunlei Liu
Magnetic Resonance in Medicine, 2019.
Quantitative Susceptibility Mapping of Articular Cartilage in Patients with Osteoarthritis at 3 Tesla
Hongjiang Wei, Huimin Lin, Le Qin, Steven Cao, Yuyao Zhang, Naying He, Weibo Chen, Fuhua Yan, Chunlei Liu
Journal of Magnetic Resonance Imaging, 2019.
Teaching Assistant, EECS 126: Probability (Spring 2020)
Teaching Assistant, EECS 16A: Linear Algebra and Circuits (Spring 2019)