Humans have been shown to give contrastive explanations, which explain why an
observed event happened rather than some other counterfactual event (the
contrast case). Despite the influential role that contrastivity plays in how
humans explain, this property is largely missing from current methods for
explaining NLP models. We present Minimal Contrastive Editing (MiCE), a method
for producing contrastive explanations of model predictions in the form of
edits to inputs that change model outputs to the contrast case. Our experiments
across three tasks--binary sentiment classification, topic classification, and
multiple-choice question answering--show that MiCE is able to produce edits
that are not only contrastive, but also minimal and fluent, consistent with
human contrastive edits. We demonstrate how MiCE edits can be used for two use
cases in NLP system development--debugging incorrect model outputs and
uncovering dataset artifacts--and thereby illustrate that producing contrastive
explanations is a promising research direction for model interpretability.

该论文介绍了一种基于最小对比编辑（MiCE）的方法，用于以编辑输入的形式产生模型预测的对比解释，以修改模型输出到对比案例。MiCE 不仅是对比的，还是最小的和流利的，与人类对比编辑一致。该方法可以用于 NLP 系统开发中的两种用例：调试错误的模型输出和揭示数据集人工因素，从而表明产生对比解释是模型解释性的一个有前途的研究方向。