Xiaodan Zhu (Queen's University) - Natural Language Inference: Some Recent Topics

Xiaodan Zhu (Queen's University)
Natural Language Inference: Some Recent Topics
Recorded November 13, 2020
Abstract: Reasoning has been a central topic in artificial intelligence from the start. Modelling informal reasoning expressed in natural language has long been a challenging problem in natural language processing. In this talk I will discuss our recent research on two topics: (1) developing end-to-end differentiable natural language inference models based on natural logic, i.e., neural natural logic models, and; (2) performing natural language inference over unstructured text and structured data (e.g., tables).
Bio: Dr. Xiaodan Zhu is an assistant professor of the Electrical and Computer Engineering Department and the Ingenuity Labs Research Institute at Queen’s University. He leads the Text Analytics and Machine Learning Lab (TAML) at Queen’s University. Dr. Zhu’s research interests are in NLP, machine learning, and artificial intelligence. He received his Ph.D. from the Department of Computer Science of the University of Toronto in 2010 and M.Eng. from the Department of Computer Science of Tsinghua University in 2000. He worked at National Research Council Canada (NRC) as a research scientist from 2010 to 2017.