Completion Reasoning Emulation for the Description Logic EL+

TL;DR

This paper introduces a method that uses deep learning to emulate reasoning processes in the EL+ description logic, enabling inspection of reasoning steps and demonstrating robustness to noisy data.

Contribution

It presents a novel approach to mimic reasoning in EL+ using LSTM neural networks, bridging symbolic reasoning and deep learning.

Findings

LSTM successfully learns EL+ reasoning patterns

The system resists noise in test data

Emulation of reasoning structure is feasible

Abstract

We present a new approach to integrating deep learning with knowledge-based systems that we believe shows promise. Our approach seeks to emulate reasoning structure, which can be inspected part-way through, rather than simply learning reasoner answers, which is typical in many of the black-box systems currently in use. We demonstrate that this idea is feasible by training a long short-term memory (LSTM) artificial neural network to learn EL+ reasoning patterns with two different data sets. We also show that this trained system is resistant to noise by corrupting a percentage of the test data and comparing the reasoner's and LSTM's predictions on corrupt data with correct answers.