Seminar • Artificial Intelligence • Reading to Learn: Improving Generalization by Learning From Language
Please note: This seminar will take place in DC 1304 and virtually over Zoom.
Victor Zhong, PhD candidate
Natural Language Processing Group, University of Washington
Traditional machine learning systems are trained on vast quantities of annotated data or experience. These systems often do not generalize to new, related problems that emerge after training, such as conversing about new topics or interacting with new environments.