Please use this identifier to cite or link to this item: https://doi.org/10.1016/S0893-6080(99)00022-2
Title: Text compression via alphabet re-representation
Authors: Long, P.M. 
Natsev, A.I.
Vitter, J.S.
Keywords: Alphabet re-representation
Machine learning
Neural networks
Over-fitting
Text compression
Issue Date: 1999
Source: Long, P.M., Natsev, A.I., Vitter, J.S. (1999). Text compression via alphabet re-representation. Neural Networks 12 (4-5) : 755-765. ScholarBank@NUS Repository. https://doi.org/10.1016/S0893-6080(99)00022-2
Abstract: This article introduces the concept of alphabet re-representation in the context of text compression. We consider re-representing the alphabet so that a representation of a character reflects its properties as a predictor of future text. This enables us to use an estimator from a restricted class to map contexts to predictions of upcoming characters. We describe an algorithm that uses this idea in conjunction with neural networks. The performance of our implementation is compared to other compression methods, such as UNIX compress, gzip, PPMC, and an alternative neural network approach.
Source Title: Neural Networks
URI: http://scholarbank.nus.edu.sg/handle/10635/39304
ISSN: 08936080
DOI: 10.1016/S0893-6080(99)00022-2
Appears in Collections:Staff Publications

Show full item record
Files in This Item:
There are no files associated with this item.

SCOPUSTM   
Citations

4
checked on Jan 16, 2018

WEB OF SCIENCETM
Citations

2
checked on Nov 23, 2017

Page view(s)

51
checked on Jan 21, 2018

Google ScholarTM

Check

Altmetric


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.