Combining symbolic human knowledge with neural networks provides a rule-based ante-hoc explanation of the output. In this paper, we propose feature extracting functions for integrating human knowledge abstracted as logic rules into the predictive behaviour of a neural network. These functions are embodied as programming functions, which represent the applicable domain knowledge as a set of logical instructions and provide a modified distribution of independent features on input data. Unlike other existing neural logic approaches, the programmatic nature of these functions implies that they do not require any kind of special mathematical encoding, which makes our method very general and flexible in nature. We illustrate the performance of our approach for sentiment classification and compare our results to those obtained using two baselines.
History
Volume
12644
Pagination
98-107
Location
Online from Padua, Italy
Start date
2021-01-21
End date
2021-01-22
ISSN
0302-9743
eISSN
1611-3349
ISBN-13
9783030739720
Language
eng
Publication classification
E1 Full written paper - refereed
Editor/Contributor(s)
Torsello A, Rossi L, Pelillo M, Biggio B, Robles-Kelly A
Title of proceedings
S+SSPR 2021 : Proceedings from the Joint IAPR Structural, Syntactic, and Statistical Pattern Recognition International Workshop
Event
Structural, Syntactic, and Statistical Pattern Recognition. Workshop (2021 : Online from Padua, Italy)