Bridging the Gap between Human and Data with AI

15 Feb
Thursday, 02/15/2018 4:00pm to 5:00pm
Computer Science Building, Room 151
Speaker: Yu Su


Data-driven problem solving and decision making is ubiquitous in daily life. For example, doctors make diagnostic decisions by gathering information from patient inquiry and examination. The rise of big data, such as electronic medical records and digitized scientific literature, bears the promise of bringing unprecedented opportunities for better-informed decision making. However, as data becomes more and more massive and heterogeneous, standing in stark contrast to this promise is the rapidly growing gap between users and data: Accessing and analyzing even very simple data requires extensive training, which is not economic for casual users who only use data on an occasional and on-demand basis. 

In this talk, he will first lay out a possible roadmap for bridging the gap between users and data, which consists of three main bottlenecks: (1) How to extract structured, actionable knowledge from raw data? (2) How to access the knowledge without programming? (3) How to reason with the knowledge? He will then discuss the key role of AI techniques in addressing these bottlenecks. More specifically, for the first bottleneck, he will discuss how to construct knowledge bases, which contain structured knowledge about entities and their relationships, from massive text data. For the second bottleneck, he will discuss how to construct natural language interfaces that allow users to query knowledge bases with natural language instead of writing SQL-like formal queries.  He will conclude the talk with future work on reasoning, including machine-aided human reasoning and knowledge-based machine reasoning.


Yu Su is a Ph.D. candidate in Computer Science at the University of California, Santa Barbara. He got his bachelor degree in Computer Science from Tsinghua University in 2012. His research intersects data mining and natural language processing towards the overarching goal of democratizing data science. His recent research interests include natural language interface (to knowledge bases, relational databases, APIs, etc.) and knowledge base construction. He has been regularly publishing and serving in top data mining and natural language processing conferences. He served as co-organizer of the first workshop on Knowledge Base Construction, Reasoning and Mining at WSDM 2018. He has interned at Microsoft Research Redmond, IBM T.J. Watson Research Center, and U.S. Army Research Laboratory.

A reception for attendees will be held at 3:30 P.M. in CS 150

Faculty Host