Xiaotao Gu
PhD Candidate
Champaign, Illinois, United States
Summary
👤
Senior🎓
Top SchoolXiaotao Gu is a PhD candidate in Computer Science at UIUC specializing in knowledge mining from unstructured data, advised by Jiawei Han and formerly trained in Tsinghua’s Knowledge Engineering Group. With nine years of experience spanning research and industry, he has interned at Google multiple times working on large-scale LLM pre-training acceleration, multilingual relation extraction, and automated headline generation. His work blends deep research rigor with production-facing engineering, contributing to info-extraction components such as the Aminer system and hands-on system optimization. Based in Champaign, he brings a global research pedigree—Cornell and Tsinghua collaborations—and an obsession for turning noisy text into structured knowledge that scales.
9 years of coding experience
4 years of employment as a software developer
Doctor of Philosophy - PhD, Computer Science, Doctor of Philosophy - PhD, Computer Science at University of Illinois Urbana-ChampaignBachelor's degree, Computer Science, Bachelor's degree, Computer Science at Tsinghua University
Github Skills (29)
bag-of-words10
mining10
phrases10
tagging9
normalization9
natural-language-processing7
nlp7
bert6
wikipedia-dump5
wikipedia4
dump4
python3
dmg3
extraction3
pdf2
Programming languages (3)
Github contributions (5)
xgeric/UCPhrase-exp
Feb 2021 - Nov 2021
This project provides an unsupervised framework for mining and tagging quality phrases on text corpora with pretrained language models (KDD'21).
Contributions:20 commits, 13 pushes, 13 comments in 8 months
nlpkddcorporaminingphrases
xgeric/click
Jul 2016 - Nov 2016
Contributions:137 pushes, 11 branches in 4 months
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.