[Colloquium] 12/17 TTIC Colloquium: Jordan Boyd-Graber, University of Maryland

[Mary Marre via Colloquium]

*When:    *  Monday, December 17th at 11:00 am



*Where:     *TTIC, 6045 S. Kenwood Avenue, 5th Floor, Room 526



*Who:       * Jordan Boyd-Graber, University of Maryland


*Title:*         Cooperative and Competitive Machine Learning through
Question Answering

*Abstract:* My research goal is to create machine learning algorithms that
are interpretable to humans, that can understand human strengths and
weaknesses, and can help humans improve themselves.  In this talk, I'll
discuss how we accomplish this through a trivia game called quiz bowl.
These questions are written so that they can be interrupted by someone who
knows more about the answer (unlike, say, Jeopardy!); that is, harder clues
are at the start of the question and easier clues are at the end of the
question: a player must decide when it has enough information to "buzz in".
Our system determines the right answer, uses deep reinforcement to
determine when to buzz, and can beat the best humans at the game.

More importantly, this setting also helps us build systems to adapt in
cooperation and competition with humans.  If we give humans access to the
predictions of our question answering system, we can craft adversarial that
remain natural for humans to answer but very
challenging for computer.  The game of quiz bowl also allows opportunities
to better understand interpretability in deep learning models to *help*
human players perform better with machine cooperation.  This cooperation
helps us with a related task, simultaneous machine translation.

Finally, I'll discuss opportunities for broader participation through open
human-computer competitions: http://qanta.org/

*Bio: *Jordan Boyd-Graber is an associate professor in the University of
Maryland's Computer Science Department, iSchool, UMIACS, and Language
Science Center. Jordan's research focus is in applying machine learning and
Bayesian probabilistic models to problems that help us better understand
social interaction or the human cognitive process. He and his students have
won "best of" awards at UAI (2018), NIPS (2009, 2015), NAACL (2016), and
CoNLL (2015), and Jordan won the British Computing Society's 2015 Karen
Spärk Jones Award and a 2017 NSF CAREER award. His research has been funded
by DARPA, IARPA, NSF, NCSES, ARL, NIH, and Lockheed Martin and has been
featured by CNN, Huffington Post, New York Magazine, and the Wall Street
Journal.


*Host:* Kevin Gimpel <kgimpel at ttic.edu>



For more information on the colloquium series or to subscribe to the
mailing list,please see http://www.ttic.edu/colloquium.php




Mary C. Marre
Administrative Assistant
*Toyota Technological Institute*
*6045 S. Kenwood Avenue*
*Room 517*
*Chicago, IL  60637*
*p:(773) 834-1757*
*f: (773) 357-6970*
*mmarre at ttic.edu <mmarre at ttic.edu>*
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://mailman.cs.uchicago.edu/pipermail/colloquium/attachments/20181210/deb6c71f/attachment.html>