Ontology-based Interpretable Machine Learning for Textual Data

Document Type

Conference Proceeding

Publication Date

7-1-2020

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.

Identifier

85093817933 (Scopus)

ISBN

[9781728169262]

Publication Title

Proceedings of the International Joint Conference on Neural Networks

External Full Text Location

https://doi.org/10.1109/IJCNN48605.2020.9206753

Grant

CNS-1747798

Fund Ref

Wells Fargo

This document is currently not available here.

Share

COinS