Deep Learning for Natural Language Inference

Speaker:   Prof. Xiaodan Zhu

Time:       10:00-11:00, Aug. 19

Location:  SIST 1A 212

Host:       Prof. Xuming He

Abstract:

Reasoning and inference are central to both human and artificial intelligence (AI). Modeling inference in natural language is notoriously challenging but is a basic problem towards true natural language understanding, as pointed out by MacCartney and Manning (2008), “a necessary (if not sufficient) condition for true natural language understanding is a mastery of open-domain natural language inference.”

In this talk, he will introduce the state-of-the-art deep learning models for natural language inference (NLI). The talk will start with a more fundamental problems: semantic representation and composition, to lay the basis for our discussion. The talk will then focus on how deep learning models achieve the state-of-the-art performance and its potential limitations..

Bio:

Xiaodan Zhu is an Assistant Professor of the Department of Electrical and Computer Engineering (ECE), Queen’s University, Canada. His research interests include, Natural Language Processing, Machine Learning, and Artificial Intelligence. Dr. Zhu received his Ph.D. from the Department of Computer Science at the University of Toronto in 2010 and his Master’s degree from the Department of Computer Science and Technology at Tsinghua University in 2000.

He recently serves as a Chair for The 33rd Canadian Conference on Artificial Intelligence. He served for ACL '19 Best Paper Award Committee. He has been as an Associate Editor for the Computational Intelligence journal since 2015. He is Co-Chair for SemEval '20, '19; Publication Chair for COLING '18; Area Chair for ACL '19, '18, EMNLP '19, NAACL '19, and COLING '18; Workshop Chair for COLING '20, PC Co-Chair for CCKS '19 (China Conference on Knowledge Graph and Semantic Computing).

SIST-Seminar 18194