Using machine learning for automated detection of ambiguity in building requirements

Zijing Zhang; Ling Ma

doi:10.35490/EC3.2023.211

Using machine learning for automated detection of ambiguity in building requirements

Zijing Zhang, Ling Ma

Civil Engineering

Research output: Chapter in Book/Published conference output › Conference publication

Abstract

The rule interpretation step is yet to be fully automated in the compliance checking process, which hinders the automation of compliance checking. Whilst existing research has developed numerous methods for automated interpretation of building requirements, none of them can identify or address ambiguous requirements. As part of interpreting ambiguous clauses automatically, this research proposed a supervised machine learning method to detect ambiguity automatically, where the bestperforming model achieved recall, precision and accuracy scores of 99.0%, 71.1%, and 78.2%, respectively. This research contributes to the body of knowledge by developing a method for automated detection of ambiguity in building requirements to support automated compliance checking.

Original language	English
Title of host publication	Proceedings of the 2023 European Conference on Computing in Construction and the 40th International CIB W78 Conference
Editors	Mohamad Kassem, Lavinia Chiara Tagliabue, Robert Amor, Marijana Sreckovic, Athanasios Chassiakos
Number of pages	7
DOIs	https://doi.org/10.35490/EC3.2023.211
Publication status	Published - 10 Jul 2023
Event	2023 European Conference on Computing in Construction and Summer School 2023 CIB W78 40th International Conference and Charles M. Eastman PhD Award - Heraklion, Greece Duration: 10 Jul 2023 → 12 Jul 2023

Publication series

Name	Proceedings of the European Conference on Computing in Construction
Volume	2023
ISSN (Electronic)	2684-1150

Conference

Conference	2023 European Conference on Computing in Construction and Summer School 2023 CIB W78 40th International Conference and Charles M. Eastman PhD Award
Country/Territory	Greece
City	Heraklion
Period	10/07/23 → 12/07/23

Access to Document

10.35490/EC3.2023.211

Cite this

Zhang, Z., & Ma, L. (2023). Using machine learning for automated detection of ambiguity in building requirements. In M. Kassem, L. C. Tagliabue, R. Amor, M. Sreckovic, & A. Chassiakos (Eds.), Proceedings of the 2023 European Conference on Computing in Construction and the 40th International CIB W78 Conference (Proceedings of the European Conference on Computing in Construction; Vol. 2023). https://doi.org/10.35490/EC3.2023.211

Zhang, Zijing ; Ma, Ling. / Using machine learning for automated detection of ambiguity in building requirements. Proceedings of the 2023 European Conference on Computing in Construction and the 40th International CIB W78 Conference. editor / Mohamad Kassem ; Lavinia Chiara Tagliabue ; Robert Amor ; Marijana Sreckovic ; Athanasios Chassiakos. 2023. (Proceedings of the European Conference on Computing in Construction).

@inproceedings{8b2ba5cec8ed4320aa1d529105d738e2,

title = "Using machine learning for automated detection of ambiguity in building requirements",

abstract = "The rule interpretation step is yet to be fully automated in the compliance checking process, which hinders the automation of compliance checking. Whilst existing research has developed numerous methods for automated interpretation of building requirements, none of them can identify or address ambiguous requirements. As part of interpreting ambiguous clauses automatically, this research proposed a supervised machine learning method to detect ambiguity automatically, where the bestperforming model achieved recall, precision and accuracy scores of 99.0%, 71.1%, and 78.2%, respectively. This research contributes to the body of knowledge by developing a method for automated detection of ambiguity in building requirements to support automated compliance checking.",

author = "Zijing Zhang and Ling Ma",

year = "2023",

month = jul,

day = "10",

doi = "10.35490/EC3.2023.211",

language = "English",

isbn = "9780701702731",

series = "Proceedings of the European Conference on Computing in Construction",

editor = "Mohamad Kassem and Tagliabue, {Lavinia Chiara} and Robert Amor and Marijana Sreckovic and Athanasios Chassiakos",

booktitle = "Proceedings of the 2023 European Conference on Computing in Construction and the 40th International CIB W78 Conference",

note = "2023 European Conference on Computing in Construction and Summer School 2023 CIB W78 40th International Conference and Charles M. Eastman PhD Award ; Conference date: 10-07-2023 Through 12-07-2023",

}

Zhang, Z & Ma, L 2023, Using machine learning for automated detection of ambiguity in building requirements. in M Kassem, LC Tagliabue, R Amor, M Sreckovic & A Chassiakos (eds), Proceedings of the 2023 European Conference on Computing in Construction and the 40th International CIB W78 Conference. Proceedings of the European Conference on Computing in Construction, vol. 2023, 2023 European Conference on Computing in Construction and Summer School 2023 CIB W78 40th International Conference and Charles M. Eastman PhD Award, Heraklion, Greece, 10/07/23. https://doi.org/10.35490/EC3.2023.211

Using machine learning for automated detection of ambiguity in building requirements. / Zhang, Zijing; Ma, Ling.
Proceedings of the 2023 European Conference on Computing in Construction and the 40th International CIB W78 Conference. ed. / Mohamad Kassem; Lavinia Chiara Tagliabue; Robert Amor; Marijana Sreckovic; Athanasios Chassiakos. 2023. (Proceedings of the European Conference on Computing in Construction; Vol. 2023).

Research output: Chapter in Book/Published conference output › Conference publication

TY - GEN

T1 - Using machine learning for automated detection of ambiguity in building requirements

AU - Zhang, Zijing

AU - Ma, Ling

PY - 2023/7/10

Y1 - 2023/7/10

N2 - The rule interpretation step is yet to be fully automated in the compliance checking process, which hinders the automation of compliance checking. Whilst existing research has developed numerous methods for automated interpretation of building requirements, none of them can identify or address ambiguous requirements. As part of interpreting ambiguous clauses automatically, this research proposed a supervised machine learning method to detect ambiguity automatically, where the bestperforming model achieved recall, precision and accuracy scores of 99.0%, 71.1%, and 78.2%, respectively. This research contributes to the body of knowledge by developing a method for automated detection of ambiguity in building requirements to support automated compliance checking.

AB - The rule interpretation step is yet to be fully automated in the compliance checking process, which hinders the automation of compliance checking. Whilst existing research has developed numerous methods for automated interpretation of building requirements, none of them can identify or address ambiguous requirements. As part of interpreting ambiguous clauses automatically, this research proposed a supervised machine learning method to detect ambiguity automatically, where the bestperforming model achieved recall, precision and accuracy scores of 99.0%, 71.1%, and 78.2%, respectively. This research contributes to the body of knowledge by developing a method for automated detection of ambiguity in building requirements to support automated compliance checking.

UR - https://ec-3.org/publications/conference/paper/?id=EC32023_211

UR - http://www.scopus.com/inward/record.url?scp=85177242179&partnerID=8YFLogxK

U2 - 10.35490/EC3.2023.211

DO - 10.35490/EC3.2023.211

M3 - Conference publication

AN - SCOPUS:85177242179

SN - 9780701702731

T3 - Proceedings of the European Conference on Computing in Construction

BT - Proceedings of the 2023 European Conference on Computing in Construction and the 40th International CIB W78 Conference

A2 - Kassem, Mohamad

A2 - Tagliabue, Lavinia Chiara

A2 - Amor, Robert

A2 - Sreckovic, Marijana

A2 - Chassiakos, Athanasios

T2 - 2023 European Conference on Computing in Construction and Summer School 2023 CIB W78 40th International Conference and Charles M. Eastman PhD Award

Y2 - 10 July 2023 through 12 July 2023

ER -

Zhang Z, Ma L. Using machine learning for automated detection of ambiguity in building requirements. In Kassem M, Tagliabue LC, Amor R, Sreckovic M, Chassiakos A, editors, Proceedings of the 2023 European Conference on Computing in Construction and the 40th International CIB W78 Conference. 2023. (Proceedings of the European Conference on Computing in Construction). doi: 10.35490/EC3.2023.211

Using machine learning for automated detection of ambiguity in building requirements

Abstract

Publication series

Conference

Access to Document

Other files and links

Fingerprint

Cite this