Language Technologies Institute Colloquium
Speaker
ANA MARASOVIĆ
Postdoctoral Researcher
Allen Institute for AI (AI2), and
Paul G. Allen School of Computer Science & Engineering
University of Washington
When
-
Where
In Person Viewing and Virtual - ET
Description
Since it is increasingly harder to opt out from interacting with AI technology, people demand that AI is capable of maintaining contracts such as that AI supports agency and oversight of people who are required to use it or who are affected by it. To help those people create a mental model about how to interact with AI systems, I extend the underlying models to self-explain---predict the label/answer and explain this prediction. In this talk, I will present how to generate (1) free-text explanations given in plain English that immediately tell users the gist of the reasoning, and (2) contrastive explanations that help users understand how they could change the text to get another label.
—
Ana Marasović is a postdoctoral researcher at the Allen Institute for AI (AI2) and the Paul G. Allen School of Computer Science & Engineering at University of Washington, and incoming assistant professor at the University of Utah. Her research interests broadly lie in the fields of natural language processing, explainable AI, and vision-and-language learning. Her projects are motivated by a unified goal: improve interaction and control of the NLP systems to help people make these systems do what they want with the confidence that they’re getting exactly what they need. Prior to joining AI2, Ana obtained her PhD from Heidelberg University.
The LTI Colloquium is generously sponsored by Abridge.
In Person Viewing and Zoom Participation. See announcement.