Robust text classification using a hysteresis-driven extended SRN

Authors:
Garen Arevian;Christo Panchev
Affiliations:
University of Sunderland, School of Computing and Technology, Sunderland, United Kingdom;University of Sunderland, School of Computing and Technology, Sunderland, United Kingdom
Venue:
ICANN'07 Proceedings of the 17th international conference on Artificial neural networks
Year:
2007

Citing 13
Cited 0

Methods in Neuronal Modeling: From synapses to networks

Methods in Neuronal Modeling: From synapses to networks
Computer systems that learn: classification and prediction methods from statistics, neural nets, machine learning, and expert systems

Computer systems that learn: classification and prediction methods from statistics, neural nets, machine learning, and expert systems
Local feedback multilayered networks

Neural Computation
Automated learning of decision rules for text categorization

ACM Transactions on Information Systems (TOIS)
Hybrid neural plausibility networks for news agents

AAAI '99/IAAI '99 Proceedings of the sixteenth national conference on Artificial intelligence and the eleventh Innovative applications of artificial intelligence conference innovative applications of artificial intelligence
Machine learning in automated text categorization

ACM Computing Surveys (CSUR)
Information Retrieval

Information Retrieval
Computational Explorations in Cognitive Neuroscience: Understanding the Mind by Simulating the Brain

Computational Explorations in Cognitive Neuroscience: Understanding the Mind by Simulating the Brain
Learning to Classify Text Using Support Vector Machines: Methods, Theory and Algorithms

Learning to Classify Text Using Support Vector Machines: Methods, Theory and Algorithms
Introduction to Modern Information Retrieval

Introduction to Modern Information Retrieval
Noisy Time Series Prediction using Recurrent Neural Networks and Grammatical Inference

Machine Learning
Statistical Comparisons of Classifiers over Multiple Data Sets

The Journal of Machine Learning Research
Bootstrapping confidence intervals for clinical input variable effects in a network trained to identify the presence of acute myocardial infarction

Neural Computation

Quantified Score

Hi-index	0.02

Visualization

Abstract

Recurrent Neural Network (RNN) models have been shown to perform well on artificial grammars for sequential classification tasks over long-term time-dependencies. However, there is a distinct lack of the application of RNNs to real-world text classification tasks. This paper presents results on the capabilities of extended two-context layer SRN models (xRNN) applied to the classification of the Reuters-21578 corpus. The results show that the introduction of high levels of noise to sequences of words in titles, where noise is defined as the unimportant stopwords found in natural language text, is very robustly handled by the classifiers which maintain consistent levels of performance. Comparisons are made with SRN and MLP models, as well as other existing classifiers for the text classification task.