A comparison of a novel neural spell checker and standard spell checking algorithms

V.J. Hodge; J. Austin

doi:10.1016/S0031-3203(01)00174-1

A comparison of a novel neural spell checker and standard spell checking algorithms

V.J. Hodge, J. Austin

Computer Science

Research output: Contribution to journal › Article › peer-review

Abstract

In this paper, we propose a simple and flexible spell checker using efficient associative matching in the AURA modular neural system. Our approach aims to provide a pre-processor for an information retrieval (IR) system allowing the user's query to be checked against a lexicon and any spelling errors corrected, to prevent wasted searching. IR searching is computationally intensive so much so that if we can prevent futile searches we can minimise computational cost. We evaluate our approach against several commonly used spell checking techniques for memory-use, retrieval speed and recall accuracy. The proposed methodology has low memory use, high speed for word presence checking, reasonable speed for spell checking and a high recall rate.

Original language	English
Pages (from-to)	2571-2580
Number of pages	9
Journal	Pattern recognition
Volume	35
Issue number	11
DOIs	https://doi.org/10.1016/S0031-3203(01)00174-1
Publication status	Published - Nov 2002

Bibliographical note

Copyright © 2002 Pattern Recognition Society. Published by Elsevier Science Ltd. This is an author produced version of a paper published in Pattern Recognition. This paper has been peer-reviewed but does not include the final publisher proof-corrections or journal pagination.

Keywords

binary neural spell checker
associative matching
supervised learning
accuracy
memory usage

Access to Document

10.1016/S0031-3203(01)00174-1

hodgevj10.pdf

http://dx.doi.org/10.1016/S0031-3203(01)00174-1

Cite this

@article{f74acd3ce3fd43e6a25ec7b9b9e74c0c,

title = "A comparison of a novel neural spell checker and standard spell checking algorithms",

abstract = "In this paper, we propose a simple and flexible spell checker using efficient associative matching in the AURA modular neural system. Our approach aims to provide a pre-processor for an information retrieval (IR) system allowing the user's query to be checked against a lexicon and any spelling errors corrected, to prevent wasted searching. IR searching is computationally intensive so much so that if we can prevent futile searches we can minimise computational cost. We evaluate our approach against several commonly used spell checking techniques for memory-use, retrieval speed and recall accuracy. The proposed methodology has low memory use, high speed for word presence checking, reasonable speed for spell checking and a high recall rate.",

keywords = "binary neural spell checker, associative matching, supervised learning, accuracy, memory usage",

author = "V.J. Hodge and J. Austin",

note = "Copyright {\textcopyright} 2002 Pattern Recognition Society. Published by Elsevier Science Ltd. This is an author produced version of a paper published in Pattern Recognition. This paper has been peer-reviewed but does not include the final publisher proof-corrections or journal pagination.",

year = "2002",

month = nov,

doi = "10.1016/S0031-3203(01)00174-1",

language = "English",

volume = "35",

pages = "2571--2580",

journal = "Pattern recognition",

issn = "0031-3203",

publisher = "Elsevier",

number = "11",

}

TY - JOUR

T1 - A comparison of a novel neural spell checker and standard spell checking algorithms

AU - Hodge, V.J.

AU - Austin, J.

N1 - Copyright © 2002 Pattern Recognition Society. Published by Elsevier Science Ltd. This is an author produced version of a paper published in Pattern Recognition. This paper has been peer-reviewed but does not include the final publisher proof-corrections or journal pagination.

PY - 2002/11

Y1 - 2002/11

N2 - In this paper, we propose a simple and flexible spell checker using efficient associative matching in the AURA modular neural system. Our approach aims to provide a pre-processor for an information retrieval (IR) system allowing the user's query to be checked against a lexicon and any spelling errors corrected, to prevent wasted searching. IR searching is computationally intensive so much so that if we can prevent futile searches we can minimise computational cost. We evaluate our approach against several commonly used spell checking techniques for memory-use, retrieval speed and recall accuracy. The proposed methodology has low memory use, high speed for word presence checking, reasonable speed for spell checking and a high recall rate.

AB - In this paper, we propose a simple and flexible spell checker using efficient associative matching in the AURA modular neural system. Our approach aims to provide a pre-processor for an information retrieval (IR) system allowing the user's query to be checked against a lexicon and any spelling errors corrected, to prevent wasted searching. IR searching is computationally intensive so much so that if we can prevent futile searches we can minimise computational cost. We evaluate our approach against several commonly used spell checking techniques for memory-use, retrieval speed and recall accuracy. The proposed methodology has low memory use, high speed for word presence checking, reasonable speed for spell checking and a high recall rate.

KW - binary neural spell checker

KW - associative matching

KW - supervised learning

KW - accuracy

KW - memory usage

U2 - 10.1016/S0031-3203(01)00174-1

DO - 10.1016/S0031-3203(01)00174-1

M3 - Article

SN - 0031-3203

VL - 35

SP - 2571

EP - 2580

JO - Pattern recognition

JF - Pattern recognition

IS - 11

ER -