A comparison of standard spell checking algorithms and a novel binary neural approach

V.J. Hodge; J. Austin

doi:10.1109/TKDE.2003.1232265

A comparison of standard spell checking algorithms and a novel binary neural approach

V.J. Hodge, J. Austin

Computer Science

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

Abstract

In this paper, we propose a simple, flexible, and efficient hybrid spell checking methodology based upon phonetic matching, supervised learning, and associative matching in the AURA neural system. We integrate Hamming Distance and n-gram algorithms that have high recall for typing errors and a phonetic spell-checking algorithm in a single novel architecture. Our approach is suitable for any spell checking application though aimed toward isolated word error correction, particularly spell checking user queries in a search engine. We use a novel scoring scheme to integrate the retrieved words from each spelling approach and calculate an overall score for each matched word. From the overall scores, we can rank the possible matches. In this paper, we evaluate our approach against several benchmark spellchecking algorithms for recall accuracy. Our proposed hybrid methodology has the highest recall rate of the techniques evaluated. The method has a high recall rate and low-computational cost.

Original language	English
Pages (from-to)	1073-1081
Number of pages	8
Journal	IEEE Transactions on Knowledge and Data Engineering
Volume	15
Issue number	5
DOIs	https://doi.org/10.1109/TKDE.2003.1232265
Publication status	Published - Sept 2003

Bibliographical note

Copyright © 2003 IEEE. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the IEEE.

Keywords

binary neural spell checker
integrated modular spell checker
associative matching
ERRORS
WORDS

Access to Document

10.1109/TKDE.2003.1232265

hodgevj2.pdf

http://dx.doi.org/10.1109/TKDE.2003.1232265

Cite this

@article{a56b1bbb164f4012aaa07a713c115bc3,

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

abstract = "In this paper, we propose a simple, flexible, and efficient hybrid spell checking methodology based upon phonetic matching, supervised learning, and associative matching in the AURA neural system. We integrate Hamming Distance and n-gram algorithms that have high recall for typing errors and a phonetic spell-checking algorithm in a single novel architecture. Our approach is suitable for any spell checking application though aimed toward isolated word error correction, particularly spell checking user queries in a search engine. We use a novel scoring scheme to integrate the retrieved words from each spelling approach and calculate an overall score for each matched word. From the overall scores, we can rank the possible matches. In this paper, we evaluate our approach against several benchmark spellchecking algorithms for recall accuracy. Our proposed hybrid methodology has the highest recall rate of the techniques evaluated. The method has a high recall rate and low-computational cost.",

keywords = "binary neural spell checker, integrated modular spell checker, associative matching, ERRORS, WORDS",

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

note = "Copyright {\textcopyright} 2003 IEEE. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the IEEE.",

year = "2003",

month = sep,

doi = "10.1109/TKDE.2003.1232265",

language = "English",

volume = "15",

pages = "1073--1081",

journal = "IEEE Transactions on Knowledge and Data Engineering",

publisher = "IEEE Computer Society",

number = "5",

}

TY - JOUR

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

AU - Hodge, V.J.

AU - Austin, J.

N1 - Copyright © 2003 IEEE. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the IEEE.

PY - 2003/9

Y1 - 2003/9

N2 - In this paper, we propose a simple, flexible, and efficient hybrid spell checking methodology based upon phonetic matching, supervised learning, and associative matching in the AURA neural system. We integrate Hamming Distance and n-gram algorithms that have high recall for typing errors and a phonetic spell-checking algorithm in a single novel architecture. Our approach is suitable for any spell checking application though aimed toward isolated word error correction, particularly spell checking user queries in a search engine. We use a novel scoring scheme to integrate the retrieved words from each spelling approach and calculate an overall score for each matched word. From the overall scores, we can rank the possible matches. In this paper, we evaluate our approach against several benchmark spellchecking algorithms for recall accuracy. Our proposed hybrid methodology has the highest recall rate of the techniques evaluated. The method has a high recall rate and low-computational cost.

AB - In this paper, we propose a simple, flexible, and efficient hybrid spell checking methodology based upon phonetic matching, supervised learning, and associative matching in the AURA neural system. We integrate Hamming Distance and n-gram algorithms that have high recall for typing errors and a phonetic spell-checking algorithm in a single novel architecture. Our approach is suitable for any spell checking application though aimed toward isolated word error correction, particularly spell checking user queries in a search engine. We use a novel scoring scheme to integrate the retrieved words from each spelling approach and calculate an overall score for each matched word. From the overall scores, we can rank the possible matches. In this paper, we evaluate our approach against several benchmark spellchecking algorithms for recall accuracy. Our proposed hybrid methodology has the highest recall rate of the techniques evaluated. The method has a high recall rate and low-computational cost.

KW - binary neural spell checker

KW - integrated modular spell checker

KW - associative matching

KW - ERRORS

KW - WORDS

U2 - 10.1109/TKDE.2003.1232265

DO - 10.1109/TKDE.2003.1232265

M3 - Article

VL - 15

SP - 1073

EP - 1081

JO - IEEE Transactions on Knowledge and Data Engineering

JF - IEEE Transactions on Knowledge and Data Engineering

IS - 5

ER -