More details: PDF version CV

Short Bio

I am a final-year Ph.D. student in Prof. Jiawei Han’s Data Mining Group at CS@Illinois, and a Google PhD Fellow. I received my B.E. from Computer Science Department, Shanghai Jiao Tong Univ. (SJTU), China, where I was a member of the 2010 ACM Honored class, now part of Zhiyuan College in SJTU.

In the past, I was lucky to collaborate with Hang Li in Huawei Noah’s Ark Lab and Tianqi Chen in University of Washington. I spent half a year working with Yu Zheng in Microsoft Research Asia. Cong Yu is my Google Research internship host. I am honored to receive the Computer Science Excellence Scholarship and Grand Prize of Yelp Dataset Challenge in 2015.

In addition, I love competitive programming contests, such as ACM/ICPC, Topcoder Open, Google Codejam, Facebook Hackercup, etc. I’m now the coach of the UIUC’s ACM/ICPC team.

My Research

My research focuses on transforming unstructured text data into structured heterogeneous information networks, on which actionable knowledge can be further uncovered flexibly and effectively based on user’s instructions. My proposed data-driven approach, with little human curation and labeling, consists of four essential steps.

  1. Language- and domain-agnostic quality phrase mining;
  2. Distant supervised named entity recognition;
  3. Data-driven, open-domain relation and attribute discovery;
  4. Construction and consolidation of heterogeneous information networks.