Past talk · AI/ML Seminar Series
Robust and Indirectly Supervised Information Extraction
Assistant Research Professor of Computer Science, University of Southern California
- Date & time
- Monday, November 14, 2022 · 1:00 PM
- Location
- Donald Bren Hall 4011
Abstract
Information extraction (IE) is the process of automatically inducing structures of concepts and relations described in natural language text. Despite its importance, obtaining direct supervision for IE tasks is difficult, as it requires expert annotators to read through long documents and identify complex structures. This talk covers recent advances that grant robustness against noise and perturbation, prevent systematic errors caused by spurious correlations, and provide indirect supervision for label-efficient and logically consistent IE.
About the speaker
Muhao Chen is an Assistant Research Professor of Computer Science at USC and director of the USC Language Understanding and Knowledge Acquisition (LUKA) Lab. His research focuses on robust and minimally supervised machine learning for natural language understanding and knowledge acquisition. His work has been recognized with an NSF CRII Award and faculty research awards from Cisco and Amazon. He obtained his Ph.D. from UCLA in 2019.