A Comparative Study of Short Text Classification with Spiking Neural Networks

Short text classification is an important task widely used in many applications. However, few works investigated applying Spiking Neural Networks (SNNs) for text classification. To the best of our knowledge, there were no attempts to apply SNNs as classifiers of short texts. In this paper, we offer...

Full description

Saved in:
Bibliographic Details
Published in2022 17th Conference on Computer Science and Intelligence Systems (FedCSIS) Vol. 30; pp. 79 - 88
Main Authors Maciag, Piotr S., Sitek, Wojciech, Skonieczny, Lukasz, Rybinski, Henryk
Format Conference Proceeding Journal Article
LanguageEnglish
Published Polish Information Processing Society 01.01.2022
Subjects
Computer science
Encoding
evolving spiking neural networks
medical documents
NeuCube
Neural networks
PubMed documents
short text classification
SNNTorch
spiking neural networks
Task analysis
Text categorization
Online AccessGet full text
ISSN2300-5963
DOI10.15439/2022F184

Cover

More Information
Summary:Short text classification is an important task widely used in many applications. However, few works investigated applying Spiking Neural Networks (SNNs) for text classification. To the best of our knowledge, there were no attempts to apply SNNs as classifiers of short texts. In this paper, we offer a comparative study of short text classification using SNNs. To this end, we selected and evaluated three popular implementations of SNNs: evolving Spiking Neural Networks (eSNN), the NeuCube implementation of SNNs, as well as the SNNTorch implementation that is available as the Python language package. In order to test the selected classifiers, we selected and preprocessed three publicly available datasets: 20-newsgroup dataset as well as imbalanced and balanced PubMed datasets of medical publications. The preprocessed 20-newsgroup dataset consists of first 100 words of each text, while for the classification of PubMed datasets we use only a title of each publication. As a text representation of documents, we applied the TF-IDF encoding. In this work, we also offered a new encoding method for eSNN networks, that can effectively encode values of input features having non-uniform distributions. The designed method works especially effectively with the TF-IDF encoding. The results of our study suggest that SNN networks may provide the classification quality is some cases matching or outperforming other types of classifiers.
ISSN:2300-5963
DOI:10.15439/2022F184