Michelle Yuan
I am an Applied Scientist at Amazon AWS AI.
I obtained my Ph.D. degree in Computer Science at the University of Maryland under the guidance of Jordan Boyd-Graber.
I have also closely worked with Benjamin Van Durme from Johns Hopkins and Hsuan-Tien Lin from NTU.
My research focuses on problems in natural language processing and machine learning.
I am interested in the intersection of transfer learning and interactive learning.
How can we adapt NLP models for new domains, languages, and tasks through human feedback?
How do we design algorithms and interfaces to easily bring a human into the loop?
Outside of computer science research, I enjoy activities like mountain climbing, rock climbing, badminton, and running. I also really like
playing the piano.
Fun fact: I have an
Erdös number of 3.
Publications/Preprints
- Samuel Barham, Orion Weller, Michelle Yuan, Kenton Murray, Mahsa Yarmohammadi, Zhengping Jiang, Siddharth Vashishtha, Alexander Martin, Anqi Liu, Aaron Steven White, Jordan Boyd-Graber, Benjamin Van Durme. MegaWika: Millions of reports and their sources across 50 diverse languages. arXiv, 2023.
[arxiv]
- Ishani Mondal, Michelle Yuan, Anandhavelu N, Aparna Garimella, Francis Ferraro, Andrew Blair-Stanek, Benjamin Van Durme, Jordan Boyd-Graber. InteractiveIE: Towards Assessing the Strength of Human-AI Collaboration in Improving the Performance of Information Extraction. arXiv, 2023.
[arxiv]
- Michelle Yuan. Transfer Learning in Natural Language Processing through Interactive Feedback. PhD Thesis, University of Maryland, 2022.
[paper]
- Michelle Yuan, Patrick Xia, Chandler May, Benjamin Van Durme, and Jordan Boyd-Graber. Adapting Coreference Resolution Models through Active Learning. Association for Computational Linguistics (long), Oral Presentation, 2022.
[paper]
[arxiv]
[code]
[video]
- 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]
Last updated:
Website design: Michelle Yuan
Photography: Michelle Yuan