Interpretable Machine Learning: Lessons from Topic Modeling

Paste the appropriate copyright statement here. ACM now supports three different copyright statements: • ACM copyright: ACM holds the copyright on the work. This is the historical approach. • License: The author(s) retain copyright, but ACM receives an exclusive publication license. • Open Access: The author(s) wish to pay for the work to be open access. The additional fee must be paid to ACM. This text field is large enough to hold the appropriate release statement assuming it is single spaced in a sans-serif 7 point font. Every submission will be assigned their own unique DOI string to be included here. Abstract This paper examines how the topic modeling community has characterized interpretability, and discusses how ideas used in topic modeling could be used to make other types of machine learning more interpretable. Interpretability is discussed both from the perspective of evaluation (“how interpretable is this model?”) and training (“how can we make this model more interpretable?”) in machine learning.