Explaining NLP Models via Minimal Contrastive Editing (MiCE)

12/27/2020
by   Alexis Ross, et al.
0

Humans give contrastive explanations that explain why an observed event happened rather than some other counterfactual event (the contrast case). Despite the important role that contrastivity plays in how people generate and evaluate explanations, this property is largely missing from current methods for explaining NLP models. We present Minimal Contrastive Editing (MiCE), a method for generating 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 – uncovering dataset artifacts and debugging incorrect model predictions – and thereby illustrate that generating contrastive explanations is a promising research direction for model interpretability.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
03/02/2021

Contrastive Explanations for Model Interpretability

Contrastive explanations clarify why an event occurred in contrast to an...
research
02/21/2018

Explanations based on the Missing: Towards Contrastive Explanations with Pertinent Negatives

In this paper we propose a novel method that provides contrastive explan...
research
11/05/2019

Why X rather than Y? Explaining Neural Model' Predictions by Generating Intervention Counterfactual Samples

Even though the topic of explainable AI/ML is very popular in text and c...
research
05/29/2019

Generating Contrastive Explanations with Monotonic Attribute Functions

Explaining decisions of deep neural networks is a hot research topic wit...
research
04/06/2021

Contrastive Explanations for Explaining Model Adaptations

Many decision making systems deployed in the real world are not static -...
research
10/01/2021

Consistent Explanations by Contrastive Learning

Understanding and explaining the decisions of neural networks are critic...
research
10/06/2020

Efficient computation of contrastive explanations

With the increasing deployment of machine learning systems in practice, ...

Please sign up or login with your details

Forgot password? Click here to reset