log in  |  register  |  feedback?  |  help  |  web accessibility
Deconstructing Complex Events through Modeling Uncertainty, States, and Outcomes
Wednesday, April 5, 2023, 11:00 am-12:00 pm Calendar
  • You are subscribed to this talk through .
  • You are watching this talk through .
  • You are subscribed to this talk. (unsubscribe, watch)
  • You are watching this talk. (unwatch, subscribe)
  • You are not subscribed to this talk. (watch, subscribe)

Situations that people experience or describe---from global, macro-level events like "financial instability" to everyday, micro-level ones like "going to dinner"---can be complex, with uncertainty in what might happen next, participant's actions affecting one another, and overlapping events contributing to an outcome. Developing a computational understanding of these situations is not straightforward. In this talk, I will present three ways that learning how to encode richer information about those descriptions can be a fruitful way of improving modeling performance, the ability to predict what events might happen next, or identify how the different participants in that situation are affected. In the first way, I will examine how event descriptions can be augmented with structural and semantic hierarchy, while accounting for uncertainty in both. In the second, I will look at how we can get models to reason about implicit states of participants in events, and reason about changes to these states as they relate to the broader situation. Finally, I will consider how we can characterize complex events by looking at participant-specific, state-based outcomes.


Frank Ferraro is an assistant professor in computer science at the University of Maryland Baltimore County (UMBC). He seeks to develop models and systems that capture common intuitions and expectations about what happens (or doesn’t) in complex situations and who (or what types of participants) may be involved. He does this through novel machine learning approaches, development of computational event semantics resources, and multi-modal (vision + language) learning approaches. Prior to UMBC, he received his PhD from Johns Hopkins University.

This talk is organized by Rachel Rudinger