@proceedings {770, title = {Completion Reasoning Emulation for the Description Logic EL+}, journal = {Proceedings of the AAAI 2020 Spring Symposium on Combining Machine Learning and Knowledge Engineering in Practice}, volume = {2600}, year = {2020}, month = {03/2020}, publisher = {CEUR-WS.org}, address = {Stanford University, Palo Alto, California, USA}, 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{\textquoteright}s and LSTM{\textquoteright}s predictions on corrupt data with correct answers.

}, keywords = {Deep Learning, Description Logic, EL+, LSTM, NeSy, Reasoning}, url = {http://ceur-ws.org/Vol-2600/paper5.pdf}, author = {Aaron Eberhart and Monireh Ebrahimi and Lu Zhou and Cogan Shimizu and Pascal Hitzler} }