Tao Yu
Assistant Professor at The University of Hong Kong
New Haven, Connecticut, United States
Summary
🤩
Rockstar🎓
Top SchoolTao Yu is an Assistant Professor of Computer Science at The University of Hong Kong and co-director of the HKU NLP Lab, with a decade of experience building and evaluating state-of-the-art natural language systems. His research and development track record spans top academic labs and industry internships (Yale, UW, Microsoft Research, Salesforce, Samsung), with particular strength in sequence-to-SQL, question answering, knowledge graphs, and text generation. He has hands-on contributions to well-known benchmarks such as the Spider text-to-SQL challenge, improving evaluation robustness by adding join-column checks and correcting annotated SQL—work that reflects a careful blend of theory and practical tooling. Trained at Yale (PhD) and Columbia (MS Data Science) and grounded in mathematics and economics, he combines rigorous quantitative thinking with applied NLP engineering. Based in New Haven, he runs an active research group and maintains a public portfolio of projects and resources for reproducible NLP research.
10 years of coding experience
5 years of employment as a software developer
The University of UtahMaster of Science (M.S.), Data Science, Master of Science (M.S.), Data Science at Columbia University in the City of New YorkDoctor of Philosophy - PhD, Computer Science - Natural Language Processing, Doctor of Philosophy - PhD, Computer Science - Natural Language Processing at Yale University
mandarin, chinese, Hakka, English
Github Skills (6)
sql10
python10
natural-language-processing9
metric9
evaluation9
nlp9
Programming languages (3)
Github contributions (5)
taoyds/spider
Sep 2018 - Mar 2022
scripts and baselines for Spider: Yale complex and cross-domain semantic parsing and text-to-SQL challenge
Role in this project:
Data Scientist
Data ScientistContributions:22 commits, 2 PRs, 28 pushes in 3 years 6 months
Contributions summary:Tao primarily contributed to the project by modifying and enhancing the evaluation scripts, focusing on SQL parsing and semantic analysis related to the "Spider" text-to-SQL challenge. They improved evaluation accuracy by incorporating join column assessments. The user also corrected annotated errors in the provided development SQL files. These changes reflect a focus on improving the accuracy and robustness of the evaluation process in a text-to-SQL context.
nlptext-to-sqlyalespidersql
taoyds/sparc
May 2020 - Mar 2022
scripts and baselines for SParC: Yale & Salesforce Semantic Parsing and Text-to-SQL in Context Challenge
Contributions:6 commits, 6 pushes in 1 year 10 months
text-to-sqlyalesparcsqlin-context
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.