Ontological-based information extraction of construction tender documents

Rosmayati Mohemad, Abdul Razak Hamdan, Zulaiha Ali Othman, Noor Maizura Mohamad Noor

Research output: Chapter in Book/Report/Conference proceedingConference contribution

5 Citations (Scopus)

Abstract

Extracting potentially relevant information either from unstructured, semi structured or structured information on construction tender documents is paramount with respect to improve decision-making processes in tender evaluation. However, various forms of information on tender documents make the information extraction process non trivial. Manually identification, aggregation and synthesize of information by decision makers is inefficient and time consuming. Thus, semantic analysis of content and document structure using domain knowledge representation is proposed to overcome the problem. The ontological-based information extraction processes contain three important components; document structure ontology, document preprocessing and information acquisition. The findings are significantly good in precision and recall which the performance measures have reached accuracy of precision about 82.35 % (concepts), 96.10 % (attributes), 100% (values) and 100 % of recall for both parameters of concepts and attributes, while 91.08 % for values.

Original languageEnglish
Title of host publicationAdvances in Intelligent and Soft Computing
Pages153-162
Number of pages10
Volume86
DOIs
Publication statusPublished - 2011

Publication series

NameAdvances in Intelligent and Soft Computing
Volume86
ISSN (Print)18675662

Fingerprint

Knowledge representation
Ontology
Agglomeration
Decision making
Semantics

Keywords

  • Construction Tender
  • Document Analysis
  • Information Extraction
  • Ontology

ASJC Scopus subject areas

  • Computer Science(all)

Cite this

Mohemad, R., Hamdan, A. R., Ali Othman, Z., & Mohamad Noor, N. M. (2011). Ontological-based information extraction of construction tender documents. In Advances in Intelligent and Soft Computing (Vol. 86, pp. 153-162). (Advances in Intelligent and Soft Computing; Vol. 86). https://doi.org/10.1007/978-3-642-18029-3_16

Ontological-based information extraction of construction tender documents. / Mohemad, Rosmayati; Hamdan, Abdul Razak; Ali Othman, Zulaiha; Mohamad Noor, Noor Maizura.

Advances in Intelligent and Soft Computing. Vol. 86 2011. p. 153-162 (Advances in Intelligent and Soft Computing; Vol. 86).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Mohemad, R, Hamdan, AR, Ali Othman, Z & Mohamad Noor, NM 2011, Ontological-based information extraction of construction tender documents. in Advances in Intelligent and Soft Computing. vol. 86, Advances in Intelligent and Soft Computing, vol. 86, pp. 153-162. https://doi.org/10.1007/978-3-642-18029-3_16
Mohemad R, Hamdan AR, Ali Othman Z, Mohamad Noor NM. Ontological-based information extraction of construction tender documents. In Advances in Intelligent and Soft Computing. Vol. 86. 2011. p. 153-162. (Advances in Intelligent and Soft Computing). https://doi.org/10.1007/978-3-642-18029-3_16
Mohemad, Rosmayati ; Hamdan, Abdul Razak ; Ali Othman, Zulaiha ; Mohamad Noor, Noor Maizura. / Ontological-based information extraction of construction tender documents. Advances in Intelligent and Soft Computing. Vol. 86 2011. pp. 153-162 (Advances in Intelligent and Soft Computing).
@inproceedings{4fcc3f7290e24a21925bd11a9d92c564,
title = "Ontological-based information extraction of construction tender documents",
abstract = "Extracting potentially relevant information either from unstructured, semi structured or structured information on construction tender documents is paramount with respect to improve decision-making processes in tender evaluation. However, various forms of information on tender documents make the information extraction process non trivial. Manually identification, aggregation and synthesize of information by decision makers is inefficient and time consuming. Thus, semantic analysis of content and document structure using domain knowledge representation is proposed to overcome the problem. The ontological-based information extraction processes contain three important components; document structure ontology, document preprocessing and information acquisition. The findings are significantly good in precision and recall which the performance measures have reached accuracy of precision about 82.35 {\%} (concepts), 96.10 {\%} (attributes), 100{\%} (values) and 100 {\%} of recall for both parameters of concepts and attributes, while 91.08 {\%} for values.",
keywords = "Construction Tender, Document Analysis, Information Extraction, Ontology",
author = "Rosmayati Mohemad and Hamdan, {Abdul Razak} and {Ali Othman}, Zulaiha and {Mohamad Noor}, {Noor Maizura}",
year = "2011",
doi = "10.1007/978-3-642-18029-3_16",
language = "English",
isbn = "9783642180286",
volume = "86",
series = "Advances in Intelligent and Soft Computing",
pages = "153--162",
booktitle = "Advances in Intelligent and Soft Computing",

}

TY - GEN

T1 - Ontological-based information extraction of construction tender documents

AU - Mohemad, Rosmayati

AU - Hamdan, Abdul Razak

AU - Ali Othman, Zulaiha

AU - Mohamad Noor, Noor Maizura

PY - 2011

Y1 - 2011

N2 - Extracting potentially relevant information either from unstructured, semi structured or structured information on construction tender documents is paramount with respect to improve decision-making processes in tender evaluation. However, various forms of information on tender documents make the information extraction process non trivial. Manually identification, aggregation and synthesize of information by decision makers is inefficient and time consuming. Thus, semantic analysis of content and document structure using domain knowledge representation is proposed to overcome the problem. The ontological-based information extraction processes contain three important components; document structure ontology, document preprocessing and information acquisition. The findings are significantly good in precision and recall which the performance measures have reached accuracy of precision about 82.35 % (concepts), 96.10 % (attributes), 100% (values) and 100 % of recall for both parameters of concepts and attributes, while 91.08 % for values.

AB - Extracting potentially relevant information either from unstructured, semi structured or structured information on construction tender documents is paramount with respect to improve decision-making processes in tender evaluation. However, various forms of information on tender documents make the information extraction process non trivial. Manually identification, aggregation and synthesize of information by decision makers is inefficient and time consuming. Thus, semantic analysis of content and document structure using domain knowledge representation is proposed to overcome the problem. The ontological-based information extraction processes contain three important components; document structure ontology, document preprocessing and information acquisition. The findings are significantly good in precision and recall which the performance measures have reached accuracy of precision about 82.35 % (concepts), 96.10 % (attributes), 100% (values) and 100 % of recall for both parameters of concepts and attributes, while 91.08 % for values.

KW - Construction Tender

KW - Document Analysis

KW - Information Extraction

KW - Ontology

UR - http://www.scopus.com/inward/record.url?scp=80052946516&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=80052946516&partnerID=8YFLogxK

U2 - 10.1007/978-3-642-18029-3_16

DO - 10.1007/978-3-642-18029-3_16

M3 - Conference contribution

AN - SCOPUS:80052946516

SN - 9783642180286

VL - 86

T3 - Advances in Intelligent and Soft Computing

SP - 153

EP - 162

BT - Advances in Intelligent and Soft Computing

ER -