Sherry Wu
Assistant Professor at Carnegie Mellon University
Pittsburgh, Pennsylvania, United States
Summary
🤩
Rockstar🎓
Top SchoolSherry Wu is an Assistant Professor at CMU HCII and a UW CS PhD who builds human-centered AI tools to help people interactively evaluate and improve NLP models. With 11 years of experience spanning research internships at Google, Microsoft Research, and Apple, she blends HCI design, front-end engineering (React/TypeScript), and ML evaluation to make model behavior more interpretable and reliable. Her open-source work includes contributions to well-known NLP testing and augmentation projects like CheckList and NL-Augmenter, where she extended evaluation engines and leaderboard tooling for robust text-classification benchmarks. She frequently bridges academic rigor with production-minded engineering, having co-advised by leaders in visualization and AI and delivered features across UI, API, and evaluation stacks. Based in Pittsburgh, she is especially interested in tooling that makes model failure modes actionable for developers and end users.
11 years of coding experience
2 years of employment as a software developer
Doctor of Philosophy (Ph.D.), Computer Science, Doctor of Philosophy (Ph.D.), Computer Science at University of WashingtonComputer Science, Junior, Computer Science, Junior at University of MichiganHigh school education, High school education at high school attched CNUHong Kong University of Science and Technology (HKUST)
Chinese, English, Chinese
Stackoverflow
1reputation
0reached
0answers
0questions
Github Skills (14)
typescript10
machine-learning10
nlp10
typescripts10
python10
text-classification10
evaluation10
natural-language-processing10
react10
typescript-types10
javascript9
huggingface9
test-automation8
data-analysis8
Programming languages (5)
Github contributions (5)
marcotcr/checklist
Apr 2020 - Mar 2021
Beyond Accuracy: Behavioral Testing of NLP models with CheckList
Role in this project:
Full-stack Developer
Full-stack DeveloperContributions:87 commits, 4 PRs, 30 pushes in 11 months
Contributions summary:Sherry appears to be working on the front-end and potentially the back-end components of the "checklist" repository, an NLP behavioral testing tool. Their commits indicate work on the UI components using React, TypeScript and also modification to the backend API and template editor. They implemented features related to the test summarizer and template editor.
nlpchecklisttestingmachine-learningbehavioral
GEM-benchmark/NL-Augmenter
Jun 2021 - Jul 2021
NL-Augmenter 🦎 → 🐍 A Collaborative Repository of Natural Language Transformations
Role in this project:ML Engineer
ML EngineerContributions:40 reviews, 7 commits, 4 PRs in 1 month
Contributions summary:Sherry's primary focus was on enhancing the evaluation engine within the NL-Augmenter repository. Their contributions involved adding return statements to evaluation functions and incorporating a simple input key argument for text classification. Further development included creating a leaderboard wrapper for organizing and printing evaluation results, as well as extending the evaluation engine to be compatible with more tasks and models, particularly in the realm of text classification. These changes aimed to improve the model evaluation process, and create leaderboards for NL augmentation tasks.
nlpinformation-theorysentencedeep-learningmachine-learning
Find and Hire Top DevelopersWe’ve analyzed the programming source code of over 60 million software developers on GitHub and scored them by 50,000 skills. Sign-up on Prog,AI to search for software developers.