12:30 -13:30 pm
Speaker: Sam Carton
Room: JCL 298
Title: The Ins and Outs of Explanations in NLP
In natural language processing (NLP) as in other areas of machine learning, the rise of large neural networks has led to increased interest in model explainability as a means to mitigate safety and ethics problems in applying such models to high-stakes decision tasks. In this talk I consider two perspectives on explanations in NLP: 1) as additional context by which humans can verify model predictions for improved human-model collaboration; and 2) as a mechanism by which to exert more fine-tuned control over model behavior–to make model predictions more robust, more aligned with human reasoning and maybe even more accurate. I argue that ultimately, these two perspectives form a virtuous circle of information flow from model to human and back, and that it is important to consider both in designing new explanation techniques and evaluations. I discuss my work on both perspectives before concluding with an agenda for future work in this area.
Sam Carton is a postdoctoral fellow working on explainable natural language processing with Chenhao Tan, initially at the University of Colorado Boulder and presently at the University of Chicago Department of Computer Science. He completed his PhD at the University of Michigan School of Information, working with Paul Resnick and Qiaozhu Mei. Sam publishes across a range of conferences from human-computer interaction to natural language processing.
[RSVP] We will also have lunch boxes from Potbelly available for the attendees! Please complete this survey to let me know that you want a box by Sunday noon 03/06: https://forms.gle/xopEhZLArweAkMci8