I am a Ph.D. candidate in Computer Science at the University of Maryland. My research focuses on problems in natural language processing and machine learning. I am advised by
Jordan Boyd-Graber and work in
CLIP lab. I have also worked with Benjamin Van Durme from Johns Hopkins and Hsuan-Tien Lin from NTU.
I am interested in transfer learning for NLP. How can we adapt models for new domains, languages, and tasks?
How do we design algorithms and interfaces to incorporate human feedback?
Outside of computer science research, I am an avid mountain climber. I grew up climbing mountains with my mom and will continue to pursue this passion.
Fun fact: I have an
Erdös number of 3.
Publications
- Michelle Yuan, Hsuan-Tien Lin, and Jordan Boyd-Graber. Cold-start Active Learning through Self-Supervised Language Modeling. Empirical Methods of Natural Language Processing (long), 2020.
[paper]
[arxiv]
[code]
[video]
- Michelle Yuan, Mozhi Zhang, Benjamin Van Durme, Leah Findlater, and Jordan Boyd-Graber. Interactive Refinement of Cross-Lingual Word Embeddings. Empirical Methods of Natural Language Processing (long), 2020.
[paper]
[arxiv]
[code]
[video]
- Michelle Yuan, Benjamin Van Durme, and Jordan Boyd-Graber. Multilingual Anchoring: Interactive Topic Modeling and Alignment Across Languages. Neural Information Processing Systems, 2018.
[paper]
[pdf]
[code]
[video]
Contact
Email: myuan (at) cs (.) umd (.) edu
Address: Iribe Center,
8125 Paint Branch Dr,
College Park, MD, 20740
Last updated:
Website design: Michelle Yuan
Photography: Michelle Yuan