About
Bang Liu is a Canada CIFAR AI Chair at Mila. He is an assistant professor in the Department of Computer Science and Operations Research (DIRO) at the University of Montreal.
Liu’s research focuses on natural language processing (NLP) and text mining, a core branch of artificial intelligence dedicated to understanding natural language. His primary research goal is to develop embodied multimodal agents (i.e., avatars) that understand grounded language. Liu has been at the forefront of designing graph representation and learning techniques for a broad range of NLP tasks, e.g., text clustering and matching for news media applications, ontology creation for searching and recommendation, text generation for machine reading comprehension. His research has been published in top-tier academic venues but has also been deployed in multiple mobile applications involving more than a billion daily active users all around the globe.
Awards
- George Walker PhD Award, University of Alberta, 2020
- J. Gordin Kaplan Graduate Student Award, University of Alberta, 2019
- Alberta Innovates - Graduate Student Scholarship, University of Alberta, 2017
- University of Alberta Doctoral Recruitment Scholarship, University of Alberta, 2016
Relevant Publications
Liu B, Han FX, Niu D, Kong L, Lai K, Xu Y. Story Forest: Extracting Events and Telling Stories from Breaking News. ACM Transactions on Knowledge Discovery from Data (TKDD). 2020 May 8;14(3):1-28.
Liu B, Niu D, Wei H, Lin J, He Y, Lai K, Xu Y. Matching Article Pairs with Graphical Decomposition and Convolutions. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, 2019 Jul (pp. 6284-6294).
Liu B, Guo W, Niu D, Luo J, Wang C, Wen Z, Xu Y. GIANT: scalable creation of a web-scale ontology. In Proceedings of the 2020 ACM SIGMOD International Conference on Management of Data, 2020 Jun 11 (pp. 393-409).
Liu B, Wei H, Niu D, Chen H, He Y. Asking questions the human way: Scalable question-answer generation from text corpus. In Proceedings of The Web Conference 2020, Apr 20 (pp. 2032-2043).
Liu B, Zhao M, Niu D, Lai K, He Y, Wei H, Xu Y. Learning to generate questions by learningwhat not to generate. In The World Wide Web Conference 2019, May 13 (pp. 1106-1118).
Support Us
CIFAR is a registered charitable organization supported by the governments of Canada, Alberta and Quebec, as well as foundations, individuals, corporations and Canadian and international partner organizations.