Research Assistant Professor of Computer Science
- 2019, Doctoral Degree, Computer Science, University of California - Los Angeles
- 2014, Bachelor's Degree, Computer Science, Fudan University
I am an Assistant Research Professor at USC Department of Computer Science, and an affliated AI researcher at USC ISI. My research focuses on data-driven machine learning approaches for processing structured data, and knowledge acquisition from unstructured data. Particularly, I am interested in developing knowledge-aware learning systems with generalizability and requiring minimal supervision, and with concrete applications to natural language understanding, knowledge base construction, computational biology and medicine. Previously, I was a Postdoctoral Fellow with Dan Roth at UPenn. I received my Ph.D. degree in Computer Science from UCLA in 2019, where I worked with Carlo Zaniolo, Kai-Wei Chang and Wei Wang. Before joining UCLA as a Ph.D. student, I graduated with a Bachelor degree from Fudan University in 2014 where I worked with X. Sean Wang.
My research group is named as the Language Understanding and Knowledge Acquisition (LUKA) Group. Recent research directions include the following:
- Robust knowledge acquisition: we study how to automatically acquire structured and actionable knowledge representations from natural language text and other structured data. Particularly, our goal is to make the learning system to require less supervision signals, be robust against training noise, provide adaptive and globally consistent inference.
- Transferable representation learning: we investigate how to capture the association of knowledge from multiple (possibly inconsistent) domains/data sources with minimal (or cheap, auxiliary) supervision, and allow complementary knowledge to be transferred across them.
- Event-Centric natural language understanding: our research in this line helps the machine understand events described in natural language. This includes the understanding of how events are connected, form processes or structure complices, and the recognition of typical properties of events (e.g., space, time, salience, essentiality, implicitness, memberships, etc.)
- AI for the common good: we apply our discoveries in NLU and data-driven machine learning in areas of biology, medicine, geology and social sciences.