The seminar is a series of both invited faculty talks and student speakers. All are welcome to attend.
The standard time is 2:00-3:00pm ET on Friday and is currently held over Zoom. The link will be sent out to the NLP mailing list. If you are not on the mailing list but would like the link, please email us.
The seminar is co-orgnaized by Emily Allaway and Fei-Tzin Lee. Please contact us with any questions.
Abstract: Interacting with humans requires being able to reason about the social implications of everyday events and situations. For example, understanding social dynamics - the relationship between people, their interactions, and behavior - allows humans to reason about ways in which to respond to a conversation partner or imagine future events that might occur. However, recent work has shown that much of this social commonsense reasoning remains a significant challenge for state-of-the-art NLP systems. In this talk, I will discuss new NLP tasks for reasoning about social dynamics including understanding character behavior in stories, generating new stories using plot dynamics, and responding empathetically to dialogue partners. I will conclude by discussing future research directions that can be explored in this area.
Bio: Hannah Rashkin is currently a research scientist at Google. In 2020, she received a PhD at the University of Washington, where she was advised by Professor Yejin Choi. Some of her research interests include commonsense reasoning about social interactions and the implications for NLP tasks such as dialogue or story generation. As a PhD student, she also worked as a research intern at the Allen Institute of Artificial Intelligence (2018-2019), Microsoft Research (2019), Facebook Artificial Intelligence Research (2018), and Pacific Northwest National Laboratory (2016).