Heuristic-based entity-relationship modelling through natural language processing

N Omar; JRP Hanna; P McKevitt

Heuristic-based entity-relationship modelling through natural language processing

N Omar
, JRP Hanna
, P McKevitt

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

576 Downloads (Pure)

Abstract

Here we propose new heuristics that assist the semi-automated generation of Entity-Relationship (ER) diagrams for database modelling from a natural language description and describe the implementation of such a system called ER-Converter. Though this is a semi-automatic transformation process, ER-Converter aims to require minimal human intervention during the process. ER-Converter has been evaluated in blind trials against a set of database problems. ER-Converter has an average of 95% recall and 82% precision. The evaluation results are discussed and demonstrate that ER-Converter could be used, for example, within the domain model of a multimedia intelligent tutoring system, designed to assist in the learning and teaching of databases.

Original language	English
Title of host publication	Unknown Host Publication
Editors	L McGinty, B Crean
Place of Publication	Dublin, Ireland
Publisher	Artificial Intelligence Association of Ireland
Pages	302-313
Number of pages	12
ISBN (Print)	1-902277-89-9
Publication status	Published (in print/issue) - Sept 2004
Event	Proc. of the 15th Artificial Intelligence and Cognitive Science Conference (AICS-04) - Galway-Mayo Institute of Technology (GMIT), Castlebar, Ireland Duration: 1 Sept 2004 → …

Conference

Conference	Proc. of the 15th Artificial Intelligence and Cognitive Science Conference (AICS-04)
Period	1/09/04 → …

Access to Document

Omaraics04Author Accepted Manuscript, 133 KB

Cite this

@inproceedings{702c9e597c234894b1cf680752cd501f,

title = "Heuristic-based entity-relationship modelling through natural language processing",

abstract = "Here we propose new heuristics that assist the semi-automated generation of Entity-Relationship (ER) diagrams for database modelling from a natural language description and describe the implementation of such a system called ER-Converter. Though this is a semi-automatic transformation process, ER-Converter aims to require minimal human intervention during the process. ER-Converter has been evaluated in blind trials against a set of database problems. ER-Converter has an average of 95\% recall and 82\% precision. The evaluation results are discussed and demonstrate that ER-Converter could be used, for example, within the domain model of a multimedia intelligent tutoring system, designed to assist in the learning and teaching of databases.",

author = "N Omar and JRP Hanna and P McKevitt",

year = "2004",

month = sep,

language = "English",

isbn = "1-902277-89-9",

pages = "302--313",

editor = "L McGinty and B Crean",

booktitle = "Unknown Host Publication",

publisher = "Artificial Intelligence Association of Ireland",

address = "Ireland",

note = "Proc. of the 15th Artificial Intelligence and Cognitive Science Conference (AICS-04) ; Conference date: 01-09-2004",

}

Omar, N, Hanna, JRP & McKevitt, P 2004, Heuristic-based entity-relationship modelling through natural language processing. in L McGinty & B Crean (eds), Unknown Host Publication. Artificial Intelligence Association of Ireland, Dublin, Ireland, pp. 302-313, Proc. of the 15th Artificial Intelligence and Cognitive Science Conference (AICS-04), 1/09/04. <http://www.4c.ucc.ie/aiai/>

TY - GEN

T1 - Heuristic-based entity-relationship modelling through natural language processing

AU - Omar, N

AU - Hanna, JRP

AU - McKevitt, P

PY - 2004/9

Y1 - 2004/9

N2 - Here we propose new heuristics that assist the semi-automated generation of Entity-Relationship (ER) diagrams for database modelling from a natural language description and describe the implementation of such a system called ER-Converter. Though this is a semi-automatic transformation process, ER-Converter aims to require minimal human intervention during the process. ER-Converter has been evaluated in blind trials against a set of database problems. ER-Converter has an average of 95% recall and 82% precision. The evaluation results are discussed and demonstrate that ER-Converter could be used, for example, within the domain model of a multimedia intelligent tutoring system, designed to assist in the learning and teaching of databases.

AB - Here we propose new heuristics that assist the semi-automated generation of Entity-Relationship (ER) diagrams for database modelling from a natural language description and describe the implementation of such a system called ER-Converter. Though this is a semi-automatic transformation process, ER-Converter aims to require minimal human intervention during the process. ER-Converter has been evaluated in blind trials against a set of database problems. ER-Converter has an average of 95% recall and 82% precision. The evaluation results are discussed and demonstrate that ER-Converter could be used, for example, within the domain model of a multimedia intelligent tutoring system, designed to assist in the learning and teaching of databases.

M3 - Conference contribution

SN - 1-902277-89-9

SP - 302

EP - 313

BT - Unknown Host Publication

A2 - McGinty, L

A2 - Crean, B

PB - Artificial Intelligence Association of Ireland

CY - Dublin, Ireland

T2 - Proc. of the 15th Artificial Intelligence and Cognitive Science Conference (AICS-04)

Y2 - 1 September 2004

ER -

Heuristic-based entity-relationship modelling through natural language processing

Abstract

Conference

Access to Document

Fingerprint

Cite this