We study continually improving an extractive question answering (QA) system via human user feedback. We design and deploy an iterative approach, where information-seeking users ask questions, receive model-predicted answers, and provide feedback. We conduct experiments involving thousands of user interactions under diverse setups to broaden the understanding of learning from feedback over time. Our experiments show effective improvement from user feedback of extractive QA models over time across different data regimes, including significant potential for domain adaptation.

Fox News Flash top headlines are here. Check out what's clicking on Foxnews.com. Umpires hastily cleared the field during a game between the Cleveland Indians and Chicago Cubs on Wednesday night when a small drone flew into Wrigley Field over the bleachers and landed on the grass in deep left center. As Willson Contreras came to bat with two outs in the bottom of the fifth and the game tied at 2, the device was spotted over the left-center stands. Before the drone landed, umpires rushed players into the dugouts.