Human-Centric Justification of Machine Learning Predictions
Human-Centric Justification of Machine Learning Predictions
Or Biran, Kathleen McKeown
Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence
Main track. Pages 1461-1467.
https://doi.org/10.24963/ijcai.2017/202
Human decision makers in many domains can make use of predictions made by machine learning models in their decision making process, but the usability of these predictions is limited if the human is unable to justify his or her trust in the prediction. We propose a novel approach to producing justifications that is geared towards users without machine learning expertise, focusing on domain knowledge and on human reasoning, and utilizing natural language generation. Through a task-based experiment, we show that our approach significantly helps humans to correctly decide whether or not predictions are accurate, and significantly increases their satisfaction with the justification.
Keywords:
Machine Learning: Classification
Machine Learning: Machine Learning
Natural Language Processing: Natural Language Generation
Multidisciplinary Topics and Applications: Validation and Verification