Completion Reasoning Emulation for the Description Logic EL+
This work addresses the challenge of making AI reasoning more interpretable and robust for knowledge-based systems, though it appears incremental as it builds on existing methods like LSTMs.
The paper tackles the problem of integrating deep learning with knowledge-based systems by emulating reasoning structure for the Description Logic EL+, demonstrating feasibility through training an LSTM on two datasets and showing resistance to noise with corrupted test data.
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.