Using Confusion Graphs to Understand Classifier Error
Davis Yoshida, Jordan Lee Boyd-Graber · 2016
Understanding the nature of the errors of a machine learning system is often difficult for multiclass classification problems with a large number of classes.This is true even more so if the number of examples for each class is low.To interpret the performance of a multiclass classifier, we form a graph representing the errors, and use average-link clustering to find groups of classes which are confused with each other.We apply this idea to the QANTA question answering system (Iyyer et al., 2014), and provide a method of analysis of the clusters.