Yuan-Fang Li (Monash)

Title: Turning information into knowledge: challenges & solutions

Abstract: Extracting structured knowledge from unstructured information such as text, speech, and images is a long-standing problem in NLP and is useful in a variety of domains and applications. This problem comes with many challenges: label scarcity, multimodality and model forgetting, to name a few. In this talk, I will discuss some of these challenges and present our recent works that address them for the tasks of event and relation extraction.

Bio: Yuan-Fang Li is an Associate Professor at the Department of Data Science and Artificial Intelligence, Faculty of Information Technology, Monash University, Australia. He is also the Associate Dean International at the faculty. His research interests include knowledge graphs, natural language processing, multimodality, and neuro-symbolic learning and reasoning. Current projects include computational approaches to understanding cross-cultural social norms and political discourse, scalable knowledge management, and multimodal information extraction. He received both his bachelor's and PhD degrees in computer science from National University of Singapore.