Continually Improving Extractive QA via Human Feedback

Ge Gao, Hung-Ting Chen, Yoav Artzi, Eunsol Choi

Submission Type: Regular Long Paper

Submission Track: Question Answering

Keywords: QA, human feedback, bandit learning

TL;DR: An iterative approach to continually improve an extractive question answering (QA) system via human user feedback.

Abstract: 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.

Submission Number: 28