Evolutionary ranking on multiple word correction algorithms using neural network approach

Jun Li; Karim Ouazzane; Yanguo Jing; Hassan Kazemian; Richard Boyd

doi:10.1007/978-3-642-03969-0_38

Evolutionary ranking on multiple word correction algorithms using neural network approach

Jun Li, Karim Ouazzane, Yanguo Jing, Hassan Kazemian, Richard Boyd

Faculty of Engineering, Environment & Computing

Research output: Chapter in Book/Report/Conference proceeding › Conference proceeding › peer-review

3 Citations (Scopus)

Abstract

Multiple algorithms have been developed to correct user's typing mistakes. However, an optimum solution is hardly identified among them. Moreover, these solutions rarely produce a single answer or share common results, and the answers may change with time and context. These have led this research to combine some distinct word correction algorithms to produce an optimal prediction based on database updates and neural network learning. In this paper, three distinct typing correction algorithms are integrated as a pilot research. Key factors including Time Change, Context Change and User Feedback are considered. Experimental results show that 57.50% Ranking First Hitting Rate (HR) with the samples of category one and a best Ranking First Hitting Rate of 74.69% within category four are achieved.

Original language	English
Title of host publication	Engineering Applications of Neural Networks
Subtitle of host publication	11th International Conference, EANN 2009, Proceedings
Editors	Dominic Palmer-Brown, Chrisina Draganova, Elias Pimenidis, Haris Mouratidis
Publisher	Springer Verlag
Pages	409-418
Number of pages	10
ISBN (Print)	3642039685, 9783642039683
DOIs	https://doi.org/10.1007/978-3-642-03969-0_38
Publication status	Published - 1 Dec 2009
Event	11th International Conference on Engineering Applications of Neural Networks, EANN 2009 - London, United Kingdom Duration: 27 Aug 2009 → 29 Aug 2009

Publication series

Name	Communications in Computer and Information Science
Volume	43 CCIS
ISSN (Print)	1865-0929

Conference

Conference	11th International Conference on Engineering Applications of Neural Networks, EANN 2009
Country/Territory	United Kingdom
City	London
Period	27/08/09 → 29/08/09

Keywords

Jaro distance
Jaro-Winkler distance
Levenshtein distance
Metaphone
Neural Network
ranking First Hitting Rate
word 2-gram

ASJC Scopus subject areas

Computer Science(all)
Mathematics(all)

Access to Document

10.1007/978-3-642-03969-0_38

Cite this

Li, J., Ouazzane, K., Jing, Y., Kazemian, H., & Boyd, R. (2009). Evolutionary ranking on multiple word correction algorithms using neural network approach. In D. Palmer-Brown, C. Draganova, E. Pimenidis, & H. Mouratidis (Eds.), Engineering Applications of Neural Networks: 11th International Conference, EANN 2009, Proceedings (pp. 409-418). (Communications in Computer and Information Science; Vol. 43 CCIS). Springer Verlag. https://doi.org/10.1007/978-3-642-03969-0_38

Evolutionary ranking on multiple word correction algorithms using neural network approach. / Li, Jun; Ouazzane, Karim; Jing, Yanguo; Kazemian, Hassan; Boyd, Richard.

Engineering Applications of Neural Networks: 11th International Conference, EANN 2009, Proceedings. ed. / Dominic Palmer-Brown; Chrisina Draganova; Elias Pimenidis; Haris Mouratidis. Springer Verlag, 2009. p. 409-418 (Communications in Computer and Information Science; Vol. 43 CCIS).

Research output: Chapter in Book/Report/Conference proceeding › Conference proceeding › peer-review

Li, J, Ouazzane, K, Jing, Y, Kazemian, H & Boyd, R 2009, Evolutionary ranking on multiple word correction algorithms using neural network approach. in D Palmer-Brown, C Draganova, E Pimenidis & H Mouratidis (eds), Engineering Applications of Neural Networks: 11th International Conference, EANN 2009, Proceedings. Communications in Computer and Information Science, vol. 43 CCIS, Springer Verlag, pp. 409-418, 11th International Conference on Engineering Applications of Neural Networks, EANN 2009, London, United Kingdom, 27/08/09. https://doi.org/10.1007/978-3-642-03969-0_38

Li J, Ouazzane K, Jing Y, Kazemian H, Boyd R. Evolutionary ranking on multiple word correction algorithms using neural network approach. In Palmer-Brown D, Draganova C, Pimenidis E, Mouratidis H, editors, Engineering Applications of Neural Networks: 11th International Conference, EANN 2009, Proceedings. Springer Verlag. 2009. p. 409-418. (Communications in Computer and Information Science). https://doi.org/10.1007/978-3-642-03969-0_38

Li, Jun ; Ouazzane, Karim ; Jing, Yanguo ; Kazemian, Hassan ; Boyd, Richard. / Evolutionary ranking on multiple word correction algorithms using neural network approach. Engineering Applications of Neural Networks: 11th International Conference, EANN 2009, Proceedings. editor / Dominic Palmer-Brown ; Chrisina Draganova ; Elias Pimenidis ; Haris Mouratidis. Springer Verlag, 2009. pp. 409-418 (Communications in Computer and Information Science).

@inproceedings{290829cd88e1445da13f6569add23fc7,

title = "Evolutionary ranking on multiple word correction algorithms using neural network approach",

abstract = "Multiple algorithms have been developed to correct user's typing mistakes. However, an optimum solution is hardly identified among them. Moreover, these solutions rarely produce a single answer or share common results, and the answers may change with time and context. These have led this research to combine some distinct word correction algorithms to produce an optimal prediction based on database updates and neural network learning. In this paper, three distinct typing correction algorithms are integrated as a pilot research. Key factors including Time Change, Context Change and User Feedback are considered. Experimental results show that 57.50% Ranking First Hitting Rate (HR) with the samples of category one and a best Ranking First Hitting Rate of 74.69% within category four are achieved.",

keywords = "Jaro distance, Jaro-Winkler distance, Levenshtein distance, Metaphone, Neural Network, ranking First Hitting Rate, word 2-gram",

author = "Jun Li and Karim Ouazzane and Yanguo Jing and Hassan Kazemian and Richard Boyd",

year = "2009",

month = dec,

day = "1",

doi = "10.1007/978-3-642-03969-0_38",

language = "English",

isbn = "3642039685",

series = "Communications in Computer and Information Science",

publisher = "Springer Verlag",

pages = "409--418",

editor = "Palmer-Brown, {Dominic } and Chrisina Draganova and Elias Pimenidis and Haris Mouratidis",

booktitle = "Engineering Applications of Neural Networks",

address = "Austria",

note = "11th International Conference on Engineering Applications of Neural Networks, EANN 2009 ; Conference date: 27-08-2009 Through 29-08-2009",

}

TY - GEN

T1 - Evolutionary ranking on multiple word correction algorithms using neural network approach

AU - Li, Jun

AU - Ouazzane, Karim

AU - Jing, Yanguo

AU - Kazemian, Hassan

AU - Boyd, Richard

PY - 2009/12/1

Y1 - 2009/12/1

N2 - Multiple algorithms have been developed to correct user's typing mistakes. However, an optimum solution is hardly identified among them. Moreover, these solutions rarely produce a single answer or share common results, and the answers may change with time and context. These have led this research to combine some distinct word correction algorithms to produce an optimal prediction based on database updates and neural network learning. In this paper, three distinct typing correction algorithms are integrated as a pilot research. Key factors including Time Change, Context Change and User Feedback are considered. Experimental results show that 57.50% Ranking First Hitting Rate (HR) with the samples of category one and a best Ranking First Hitting Rate of 74.69% within category four are achieved.

AB - Multiple algorithms have been developed to correct user's typing mistakes. However, an optimum solution is hardly identified among them. Moreover, these solutions rarely produce a single answer or share common results, and the answers may change with time and context. These have led this research to combine some distinct word correction algorithms to produce an optimal prediction based on database updates and neural network learning. In this paper, three distinct typing correction algorithms are integrated as a pilot research. Key factors including Time Change, Context Change and User Feedback are considered. Experimental results show that 57.50% Ranking First Hitting Rate (HR) with the samples of category one and a best Ranking First Hitting Rate of 74.69% within category four are achieved.

KW - Jaro distance

KW - Jaro-Winkler distance

KW - Levenshtein distance

KW - Metaphone

KW - Neural Network

KW - ranking First Hitting Rate

KW - word 2-gram

UR - http://www.scopus.com/inward/record.url?scp=78049368234&partnerID=8YFLogxK

U2 - 10.1007/978-3-642-03969-0_38

DO - 10.1007/978-3-642-03969-0_38

M3 - Conference proceeding

AN - SCOPUS:78049368234

SN - 3642039685

SN - 9783642039683

T3 - Communications in Computer and Information Science

SP - 409

EP - 418

BT - Engineering Applications of Neural Networks

A2 - Palmer-Brown, Dominic

A2 - Draganova, Chrisina

A2 - Pimenidis, Elias

A2 - Mouratidis, Haris

PB - Springer Verlag

T2 - 11th International Conference on Engineering Applications of Neural Networks, EANN 2009

Y2 - 27 August 2009 through 29 August 2009

ER -

Evolutionary ranking on multiple word correction algorithms using neural network approach

Abstract

Publication series

Conference

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this