Lunch at 12:30pm, talk at 1pm, in 148 Fitzpatrick

Title: Memories as Repositories of Events: Structural Event Knowledge Acquisition from Multimedia Data

Abstract: Human memories can be regarded as repositories of historical events. Event structures encapsulate the fundamental questions of Who, What, Where, When, and Why that humans discuss on a daily basis. However, the exploding volume of data is overwhelming, necessitating the ability of machines to automatically obtain events and their arguments (i.e., participants) from enormous unstructured data, such as text, images, videos, etc. In order to present a comprehensive understanding of events over an extended period, it is critical to enable computers to extract local event structures (i.e., who, what, where, and when) from multiple unstructured data sources, and also to perform global reasoning across events (i.e., what is likely to happen, and why). However, current event understanding is text-only, local, and lacking in reasoning. This talk focuses on developing methods to deal with real-world events that are multimedia, interconnected, probabilistic, and span a long time period. We leverage historical events to discover global event schema knowledge, such as the interaction patterns between events and the evolution patterns along a long period, which can be used as constraints for reasoning about future events. Our structural event graph modeling is able to represent the global inter-dependencies of events and long-distance interactions via arguments, leading to a comprehensive understanding of events and effective forecasting of future events.

Bio: Manling Li is a fourth-year Ph.D. student at the Computer Science Department of University of Illinois Urbana-Champaign. Manling has won the Best Demo Paper Award at ACL’20, the Best Demo Paper Award at NAACL’21, C.L. Dave and Jane W.S. Liu Award, and has been selected as Mavis Future Faculty Fellow. She is a recipient of the Microsoft Research PhD Fellowship. She has more than 30 publications on knowledge extraction and reasoning from multimedia data. Additional information is available at https://limanling.github.io.