Human Evaluation of Interpretability: The Case of AI-Generated Music Knowledge
Abstract
Interpretability of machine learning models has gained more and more attention among researchers in the artificial intelligence (AI) and human-computer interaction (HCI) communities. Most existing work focuses on decision making, whereas we consider knowledge discovery. In particular, we focus on evaluating AI-discovered knowledge/rules in the arts and humanities. From a specific scenario, we present an experimental procedure to collect and assess human-generated verbal interpretations of AI-generated music theory/rules rendered as sophisticated symbolic/numeric objects. Our goal is to reveal both the possibilities and the challenges in such a process of decoding expressive messages from AI sources. We treat this as a first step towards 1) better design of AI representations that are human interpretable and 2) a general methodology to evaluate interpretability of AI-discovered knowledge representations.
Keywords
Cite
@article{arxiv.2004.06894,
title = {Human Evaluation of Interpretability: The Case of AI-Generated Music Knowledge},
author = {Haizi Yu and Heinrich Taube and James A. Evans and Lav R. Varshney},
journal= {arXiv preprint arXiv:2004.06894},
year = {2020}
}