Semantic Explanations of Predictions

05/27/2018
by   Freddy Lecue, et al.
0

The main objective of explanations is to transmit knowledge to humans. This work proposes to construct informative explanations for predictions made from machine learning models. Motivated by the observations from social sciences, our approach selects data points from the training sample that exhibit special characteristics crucial for explanation, for instance, ones contrastive to the classification prediction and ones representative of the models. Subsequently, semantic concepts are derived from the selected data points through the use of domain ontologies. These concepts are filtered and ranked to produce informative explanations that improves human understanding. The main features of our approach are that (1) knowledge about explanations is captured in the form of ontological concepts, (2) explanations include contrastive evidences in addition to normal evidences, and (3) explanations are user relevant.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
09/22/2020

ALICE: Active Learning with Contrastive Natural Language Explanations

Training a supervised neural network classifier typically requires many ...
research
06/29/2021

Semantic Reasoning from Model-Agnostic Explanations

With the wide adoption of black-box models, instance-based post hoc expl...
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
09/16/2021

Detection Accuracy for Evaluating Compositional Explanations of Units

The recent success of deep learning models in solving complex problems a...
research
06/15/2021

Generating Contrastive Explanations for Inductive Logic Programming Based on a Near Miss Approach

In recent research, human-understandable explanations of machine learnin...
research
04/09/2021

Individual Explanations in Machine Learning Models: A Case Study on Poverty Estimation

Machine learning methods are being increasingly applied in sensitive soc...
research
08/20/2021

VAE-CE: Visual Contrastive Explanation using Disentangled VAEs

The goal of a classification model is to assign the correct labels to da...

Please sign up or login with your details

Forgot password? Click here to reset