Necessity and Sufficiency for Explaining Text Classifiers: A Case Study in Hate Speech Detection

Understand

We present a novel feature attribution method for explaining text classifiers, and analyze it in the context of hate speech detection.

• Although feature attribution models usually provide a single importance score for each token, we instead provide two complementary and theoretically-grounded scores -- necessity and sufficiency -- resulting in more informative explanations.
• We propose a transparent method that calculates these values by generating explicit perturbations of the input text, allowing the importance scores themselves to be explainable.
• We employ our method to explain the predictions of different hate speech detection models on the same set of curated examples from a test suite, and show that different values of necessity and sufficiency for identity terms correspond to different kinds of false positive errors, exposing sources of classifier bias against marginalized groups.