Crowdsourcing Deep Thoughts: Meeting the Challenges of In-depth Language Understanding Systems for Smarter Social Media

Speaker: Jamie Macbeth
Speaker Affiliation: School of Engineering, Fairfield University

Date: Friday, November 18, 2016
Time: 2:00 PM to 3:00 PM
Location: CBLS 152

Intelligent systems driven by natural language input are well-positioned to meet the challenges of intervening against abuses of social media (such as cyberbullying) and providing resources for victims. However, the language processing problems posed in these situations appear to be “Google proof”: algorithms that scrape Wikipedia or other large text corpora for surface-level language properties (e.g. frequencies or co-occurrences of words) perform poorly. This talk will discuss work to build systems that understand natural language about social situations in-depth in support of these applications. Our approach is based on a traditional symbolic method that represents deep semantics as complex combinations of simple, primitive acts, but it also uses crowdsourcing to collect these commonsense knowledge structures of human experience in a scalable and inexpensive way.

Bio:

Jamie Macbeth is an assistant professor of computer science in the School of Engineering at Fairfield University. He was previously a postdoctoral fellow at Clemson University and a postdoctoral research associate with CSAIL at MIT. He holds a Ph.D. in Computer Science from the University of California, Los Angeles, an M.S. in Physics from Stanford University, and a B.S. in Physics from Brown University. His broad interests include human-computer interaction, human factors of software engineering, and natural language understanding. He is a member of the ACM and the IEEE.