Multi-relational Knowledge Acquisition with Transferable Representation Learning

Wednesday, January 22, 2020, 11:00 am - 12:00 pm PDTiCal
1016 East CR
This event is open to the public.
AI Seminar
Muhao Chen, PhD UPENN
Video Recording:

Abstract: Multi-relational data provide structural and actionable knowledge representations for intelligent systems in various areas. As constructing such structural knowledge is often costly and has relied on extensive human efforts, there is a pressing need for approaches to support automated knowledge acquisition. Our research investigates data-driven machine learning methods to fulfill this mission, particularly from two angels: (i) As different sources of multi-relational data often possess interchangeable and complementary knowledge, our study on transferable representation learning seeks to capture the association of knowledge across multiple data sources, and further support the projection and synchronization of knowledge across different domains; (ii) We develop scalable relation induction systems to extract relational knowledge from unstructured data. In this talk, I will present several of our recent works in these two lines of research. Particularly, I will also detail in the talk how the enabling technologies benefit a wide range of tasks in areas of knowledge base population, natural language processing and computational biology.

Bio: Muhao Chen is a postdoctoral fellow at the University of Pennsylvania. He received a Ph.D. in Computer Science from the University of California Los Angeles. His research focuses on data-driven machine learning approaches for processing structured and unstructured data, and extending their applications to natural language understanding, knowledge base construction, computational biology and medical informatics. Particularly, he is interested in developing knowledge-aware learning systems with generalizability and requiring minimal supervision. Muhao has collaborated with over 50 scholars from 11 institutes, and has published over 30 research papers in leading conferences and journals. His dissertation research was awarded a UCLA Dissertation Fellowship. Before joining UCLA as a Ph.D. student, he obtained a B.S. in Computer Science from Fudan University.

Host: Jay Pujara

POC: Karen Rawlins /Jamani King

« Return to Upcoming Events