IEEE / UBC ECE Seminar

23 February 2018 @ 11:00 – 12:00
Room 418, Macleod Building
Macleod Bldg
2356 Main Mall, Vancouver, BC V6T 1Z4
Vincent Wong
IEEE / UBC ECE Seminar, co-sponsored by the IEEE Vancouver Joint Communications Chapter
Title: Story Forest: Organizing Massive News Documents via AI and Natural Language Processing
Presented by:  Prof. Di Niu, University of Alberta

Date and time:  Friday, February 23, 2018, at 11 am

Location:Room 418, Macleod Building, UBC, 2356 Main Mall, Vancouver

Abstract: I will describe our recent experience of implementing a news content organization system in collaboration with Tencent that can discover hot events from vast streams of breaking news and connect events into stories for easy viewing. Our real-world system has distinct requirements in contrast to previous studies on document topic modeling and detection, in that 1) an event does not only contain articles of a similar topic, but is a cluster of documents that report exactly the same physical incidence; 2) we must evolve news stories in a logical and online manner. In solving these challenges, we propose Story Forest, a state-of-the-art news content organization system based on artificial intelligence and natural language processing. I will briefly describe the key enabling technologies in Story Forest, including identifying the relationship between text objects, e.g., whether they talk about the same event or whether one article is a follow-up of another, based on deep learning. Our system has been deployed in Tencent QQ Browser mobile app.

Biography:  Dr. Di Niu is an Assistant Professor in the Department of Electrical and Computer Engineering at the University of Alberta, specialized in the interdisciplinary areas of machine learning, distributed systems, data mining, cloud computing and optimization algorithms. He has coauthored nearly 50 papers in top journals and conferences in computer science and engineering, including the Web Conference (WWW), AAAI, INFOCOM, CIKM, ICDM, Multimedia, SIGMETRICS, IEEE/ACM Transactions on Networking, IEEE Transactions on Parallel and Distributed Systems, IEEE Transactions on Multimedia, ACM TOMPECS, etc. He was the winner of the Extraordinary Award (No. 1 out of all 18 award holders) of the CCF-Tencent Rhino Bird Open Grant 2016 for his invention of the Story Forest system for news data understanding at scale, which has been deployed in Tencent’s products.