Towards Structured-Infused and Disentangled Representation Learning

Join remotely via BlueJeans: https://bluejeans.com/930564534

One of the keys to the empirical successes of deep neural networks in many domains, such as natural language processing and computer vision, is their ability to automatically extract salient features for downstream tasks via the end-to-end learning paradigm.

In this talk, I will present two of our recent work. First, I will introduce how to encode structured dependencies into learned representations to achieve efficient non-autoregressive machine translation models. Second, I will present our work on learning representations to decouple global and local information from/for image generation. I will conclude by laying out future research directions towards interpretable and controllable representation learning.

Bio: Xuezhe Ma is a final year PhD student at Carnegie Mellon University, advised by Eduard Hovy.

Before that, he received his B.E and M.S from Shanghai Jiao Tong University. His research interests fall in areas of natural language processing and machine learning, particularly in deep learning and representation learning with applications to linguistic structured prediction and deep generative models. Xuezhe has interned at Allen Institute for Artificial Intelligence (AI2) and earned the AI2 Outstanding Intern award. His research has been recognized with outstanding paper award at ACL 2016 and best demo paper nomination at ACL 2019.

11:30-Noon: Grad Student Round Table with the Candidate (join via BlueJeans seminar link)