QANTA:
Question Answering is Not a Trivial Activity
University of Maryland, College Park
QANTA Project
The QANTA project at the University of Maryland brings together human and computer question answering: helping computers better answer questions from learning how trivia experts answer questions, helping understand how to explain question answering in human-computer teams, and helping humans author challenging, interesting questions efficiently. Led by associate professor Dr. Jordan Boyd-Graber, the team of graduate and undergraduate students from computer science, language science, and information science build interfaces, algorithms, and datasets to improve human and computer question answering. We build computer systems that be fairly compared against each other and expert humans based on a trivia game called quiz bowl. You can see videos of our previous events against top trivia champs or read about our system:
Associate Professor Jordan Boyd-Graber to appear on Jeopardy on September 26th (2018)
UMD Computerized System Beats Human Quiz Bowl Team at Atlanta Exhibition (2017)
Question-Answering System Built by UMD, UC Boulder Bests Ken Jennings (2015)
If this sounds like fun, take part in our next competition!
QANTA Dataset
With the cooperation of the quiz bowl community, we compile datasets of questions that can challenge question answering systems. Read our preprint describing the main dataset. If you're a computer science researcher, this is likely what you came here for!
Human vs. Machine Competitions: Try it!
Want to take on the best computer programs at playing trivia? Register for our next event!
Read our preprint about the first round of the competition!
Contact Jordan Boyd-Graber or qanta@googlegroups.com for questions / concerns.