Abstract

Abstract:

Deep learning has largely improved the performance of natural language understanding (NLU) systems. However, most deep learning models are black-box machinery, and lack explicit interpretation. In this talk, I will introduce our recent progress on neuro-symbolic reasoning for NLU , which combines different schools of AI, namely, symbolism and connectionism. Generally, we will design a neural system with symbolic structures for an NLU task, and apply reinforcement learning or its relaxation to perform weakly supervised reasoning in the downstream task. Our framework has been successfully applied to various tasks, including SQL command reasoning, syntactic structure reasoning, and logical reasoning.

Bio:

Dr. Lili Mou is an Assistant Professor at the Department of Computing Science, University of Alberta. He is also an Alberta Machine Intelligence Institute (Amii) Fellow and a Canada CIFAR AI (CCAI) Chair. Lili received his BS and PhD degrees in 2012 and 2017, respectively, from School of EECS , Peking University. After that, he worked as a postdoctoral fellow at the University of Waterloo. His research interests include deep learning applied to natural language processing as well as programming language processing. He has publications at top conferences and journals, including AAAI , EMNLP, TACL , ICML, ICLR , and NeurIPS. He also presented tutorials at EMNLP ’19 and ACL ’20.