Ontology-based Interpretable Machine Learning for Textual Data

Abstract

In this paper, we introduce a novel interpreting framework that learns an interpretable model based on an ontology-based sampling technique to explain agnostic prediction models. Different from existing approaches, our algorithm considers contextual correlation among words, described in domain knowledge ontologies, to generate semantic explanations. To narrow down the search space for explanations, which is a major problem of long and complicated text data, we design a learnable anchor algorithm, to better extract explanations locally. A set of regulations is further introduced, regarding combining learned interpretable representations with anchors to generate comprehensible semantic explanations. An extensive experiment conducted on two real-world datasets shows that our approach generates more precise and insightful explanations compared with baseline approaches.

arXiv commentAccepted by IJCNN 2020

References in corpus (8)

• Adam: A Method for Stochastic Optimization
• Striving for Simplicity: The All Convolutional Net
• Learning Important Features Through Propagating Activation Differences
• "What is Relevant in a Text Document?": An Interpretable Machine Learning Approach
• Gradients of Counterfactuals
• Trepan Reloaded: A Knowledge-driven Approach to Explaining Artificial Neural Networks
• Semantic Explanations of Predictions
• LEAFAGE: Example-based and Feature importance-based Explanationsfor Black-box ML models