Explaining NLP Models via Minimal Contrastive Editing (MiCE)

Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021, pages 3840–3852 August 1–6, 2021. ©2021 Association for Computational Linguistics 3840 Explaining NLP Models via Minimal Contrastive Editing (MICE) Alexis Ross† Ana Marasovi´c†} Matthew E. Peters† †Allen Institute for Artificial Intelligence, Seattle, WA, USA }Paul G. Allen School of Computer Science and Engineering, University of Washington {alexisr,anam,matthewp}@allenai.org Abstract Humans have been shown to give contrastive explanations, which explain why an observed event happened rather than some other coun- terfactual event (the contrast case). De- spite the influential role that contrastivity plays in how humans explain, this property is largely missing from current methods for explaining NLP models. We present MIN- IMAL 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 pro- duce 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 sys- tem development—debugging incorrect model outputs and uncovering dataset artifacts—and thereby illustrate that producing contrastive ex- planations is a promising research direction for model interpretability. 1 Introduction Cognitive science and philosophy research has shown that human explanations are contrastive (Miller, 2019): People explain why an observed event happened rather than some counterfactual event called the contrast case. This contrast case plays a key role in modulating what explanations are given. Consider Figure 1. When we seek an ex- planation of the model’s prediction “by train,” we seek it not in absolute terms, but in contrast to an- other possible prediction (i.e. “on foot”). Addition- ally, we tailor our explanation to this contrast case. For instance, we might explain why the prediction is “by train” and not “on foot” by saying that the writer discusses meeting Ann at the train station Figure 1: An example MICE edit for a multiple-choice question from the RACE dataset. MICE generates con- trastive explanations in the form of edits to inputs that change model predictions to target (contrast) predic- tions. The edit (bolded in red) is minimal and fluent, and it changes the model’s prediction from “by train” to the contrast prediction “on foot” (highlighted in gray). instead of at Ann’s home on foot; such information is captured by the edit (bolded red) that results in the new model prediction “on foot.” For a differ- ent contrast prediction, such as “by car,” we would provide a different explanation. In this work, we propose to give contrastive explanations of model predictions in the form of targeted minimal edits, as shown in Figure 1, that cause the model to change its original prediction to the contrast prediction. Given the key role that contrastivity plays in human explanations, making model explanations contrastive could make them more user-centered and thus more useful for their intended purposes, such as debugging and exposing dataset …

Content truncated to 500 words