SINGLE DOCUMENT TEXT SUMMARIZATION USING RANDOM INDEXING AND NEURAL NETWORKS

Niladri Chatterjee, Avikant Bhardwaj

2010

Abstract

This paper presents a new extraction-based summarization technique developed using neural networks and Random Indexing. The technique exploits the advantages that a neural network provides in terms of compatibility and adaptability of a system as per the user. A neural network is made to learn the important properties of sentences that should be included in the summary through training. The trained neural network is then used as a sieve to filter out the sentences relevant for corresponding summary. Neural network along with Random Indexing extracts the semantic similarity between sentences in order to remove redundancy from the text to great success. One major advantage of the proposed scheme is that it takes care of human subjectivity as well.

Paper Citation

in Harvard Style

Chatterjee N. and Bhardwaj A. (2010). SINGLE DOCUMENT TEXT SUMMARIZATION USING RANDOM INDEXING AND NEURAL NETWORKS . In Proceedings of the International Conference on Knowledge Engineering and Ontology Development - Volume 1: KEOD, (IC3K 2010) ISBN 978-989-8425-29-4, pages 171-176. DOI: 10.5220/0003066601710176

in Bibtex Style

@conference{keod10,
author={Niladri Chatterjee and Avikant Bhardwaj},
title={SINGLE DOCUMENT TEXT SUMMARIZATION USING RANDOM INDEXING AND NEURAL NETWORKS},
booktitle={Proceedings of the International Conference on Knowledge Engineering and Ontology Development - Volume 1: KEOD, (IC3K 2010)},
year={2010},
pages={171-176},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0003066601710176},
isbn={978-989-8425-29-4},
}

in EndNote Style

TY - CONF
JO - Proceedings of the International Conference on Knowledge Engineering and Ontology Development - Volume 1: KEOD, (IC3K 2010)
TI - SINGLE DOCUMENT TEXT SUMMARIZATION USING RANDOM INDEXING AND NEURAL NETWORKS
SN - 978-989-8425-29-4
AU - Chatterjee N.
AU - Bhardwaj A.
PY - 2010
SP - 171
EP - 176
DO - 10.5220/0003066601710176