Please note: This PhD seminar will take place online.
Zhiying Jiang, PhD candidate
David R. Cheriton School of Computer Science
Supervisor: Professor Jimmy Lin
Deep neural networks (DNNs) are often used for text classification due to their high accuracy. However, DNNs can be computationally intensive, requiring millions of parameters and large amounts of labeled data, which can make them expensive to use, to optimize, and to transfer to out-of-distributed (OOD) cases in practice.