2023
EMNLP
EMNLP 2023
Continually Improving Extractive QA via Human Feedback
Abstract
AbstractWe 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.
🌉
Interdisciplinary Bridge
- Artificial Intelligence and Natural Language Processing
Authors
Topics
Artificial Intelligence > Core AI > Human-AI Interaction
Artificial Intelligence > Learning Paradigms > Transfer Learning
Machine Learning > Learning Types > Active Learning
Machine Learning > Learning Types > Continual Learning
Natural Language Processing > Applications > Question Answering
Machine Learning > Learning Types > Reinforcement Learning