File(s) under permanent embargo
Feature Extraction Functions for Neural Logic Rule Learning
conference contribution
posted on 2021-01-01, 00:00 authored by Shashank GuptaShashank Gupta, Antonio Robles-KellyAntonio Robles-Kelly, Mohamed Reda BouadjenekMohamed Reda BouadjenekCombining 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
Event
Structural, Syntactic, and Statistical Pattern Recognition. Workshop (2021 : Online from Padua, Italy)Volume
12644Series
Lecture Notes in Computer Science; 12644Pagination
98 - 107Publisher
Springer International PublishingLocation
Online from Padua, ItalyPlace of publication
Cham, SwitzerlandPublisher DOI
Start date
2021-01-21End date
2021-01-22ISSN
0302-9743eISSN
1611-3349ISBN-13
9783030739720Language
engPublication classification
E1 Full written paper - refereedEditor/Contributor(s)
Andrea Torsello, Luca Rossi, Marcello Pelillo, Battista Biggio, Antonio Robles-KellyTitle of proceedings
S+SSPR 2021 : Proceedings from the Joint IAPR Structural, Syntactic, and Statistical Pattern Recognition International WorkshopUsage metrics
Categories
No categories selectedLicence
Exports
RefWorks
BibTeX
Ref. manager
Endnote
DataCite
NLM
DC