Named entity recognition in construction supply chain risk management using transformer-based models and genetic algorithm-driven hyperparameter tuning

Milad Baghalzadeh Shishehgarkhaneh; Melissa Chan; Robert C. Moehler; Yihai Fang; Amer A. Hijazi; Hamed Aboutorab

doi:10.1109/ICECET61485.2024.10698305

Named entity recognition in construction supply chain risk management using transformer-based models and genetic algorithm-driven hyperparameter tuning

Milad Baghalzadeh Shishehgarkhaneh, Melissa Chan, Robert C. Moehler, Yihai Fang, Amer A. Hijazi, Hamed Aboutorab

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

1 Citation (Scopus)

Abstract

The construction industry faces significant supply chain risks, necessitating effective management strategies. This paper presents a novel approach using transformer-based models for Named Entity Recognition (NER) to identify risk-related entities within construction supply chain management (SCRM) from news articles. It specifically explores the efficacy of two transformer models, BERT and DeBERTa, and employs Genetic Algorithms (GAs) for optimizing model hyperparameters. This research underscores the transformative potential of NLP-driven solutions in enhancing SCRM, particularly within the unique context of the Australian construction industry. The findings highlight the importance of precision in entity recognition for effective SCRM and demonstrate the superiority of DeBERTa in precision-focused tasks, making it a promising tool for practitioners in this field.

Original language	English
Title of host publication	International Conference on Electrical, Computer, and Energy Technologies (ICECET 2024), 25th - 27th July, 2024, Sydney, Australia
Place of Publication	U.S.
Publisher	IEEE
Number of pages	7
ISBN (Electronic)	9798350395914
DOIs	https://doi.org/10.1109/ICECET61485.2024.10698305
Publication status	Published - 2024
Externally published	Yes
Event	International Conference on Electrical, Computer, and Energy Technologies - Sydney, Australia Duration: 25 Jul 2024 → 27 Jul 2024 Conference number: 4th

Conference

Conference	International Conference on Electrical, Computer, and Energy Technologies
Abbreviated title	ICECET
Country/Territory	Australia
City	Sydney
Period	25/07/24 → 27/07/24

Keywords

BERT
Construction Supply Chain
Genetic Algorithms
Proactive Risk Management
Transformer Models

Access to Document

10.1109/ICECET61485.2024.10698305

Cite this

Shishehgarkhaneh, M. B., Chan, M., Moehler, R. C., Fang, Y., Hijazi, A. A., & Aboutorab, H. (2024). Named entity recognition in construction supply chain risk management using transformer-based models and genetic algorithm-driven hyperparameter tuning. In International Conference on Electrical, Computer, and Energy Technologies (ICECET 2024), 25th - 27th July, 2024, Sydney, Australia IEEE. https://doi.org/10.1109/ICECET61485.2024.10698305

Shishehgarkhaneh, Milad Baghalzadeh ; Chan, Melissa ; Moehler, Robert C. et al. / Named entity recognition in construction supply chain risk management using transformer-based models and genetic algorithm-driven hyperparameter tuning. International Conference on Electrical, Computer, and Energy Technologies (ICECET 2024), 25th - 27th July, 2024, Sydney, Australia. U.S. : IEEE, 2024.

@inproceedings{fac36a261b1d4d86b2f63fb9df679d4a,

title = "Named entity recognition in construction supply chain risk management using transformer-based models and genetic algorithm-driven hyperparameter tuning",

abstract = "The construction industry faces significant supply chain risks, necessitating effective management strategies. This paper presents a novel approach using transformer-based models for Named Entity Recognition (NER) to identify risk-related entities within construction supply chain management (SCRM) from news articles. It specifically explores the efficacy of two transformer models, BERT and DeBERTa, and employs Genetic Algorithms (GAs) for optimizing model hyperparameters. This research underscores the transformative potential of NLP-driven solutions in enhancing SCRM, particularly within the unique context of the Australian construction industry. The findings highlight the importance of precision in entity recognition for effective SCRM and demonstrate the superiority of DeBERTa in precision-focused tasks, making it a promising tool for practitioners in this field.",

keywords = "BERT, Construction Supply Chain, Genetic Algorithms, Proactive Risk Management, Transformer Models",

author = "Shishehgarkhaneh, {Milad Baghalzadeh} and Melissa Chan and Moehler, {Robert C.} and Yihai Fang and Hijazi, {Amer A.} and Hamed Aboutorab",

year = "2024",

doi = "10.1109/ICECET61485.2024.10698305",

language = "English",

booktitle = "International Conference on Electrical, Computer, and Energy Technologies (ICECET 2024), 25th - 27th July, 2024, Sydney, Australia",

publisher = "IEEE",

note = "International Conference on Electrical, Computer, and Energy Technologies, ICECET ; Conference date: 25-07-2024 Through 27-07-2024",

}

Shishehgarkhaneh, MB, Chan, M, Moehler, RC, Fang, Y, Hijazi, AA & Aboutorab, H 2024, Named entity recognition in construction supply chain risk management using transformer-based models and genetic algorithm-driven hyperparameter tuning. in International Conference on Electrical, Computer, and Energy Technologies (ICECET 2024), 25th - 27th July, 2024, Sydney, Australia. IEEE, U.S., International Conference on Electrical, Computer, and Energy Technologies, Sydney, New South Wales, Australia, 25/07/24. https://doi.org/10.1109/ICECET61485.2024.10698305

Named entity recognition in construction supply chain risk management using transformer-based models and genetic algorithm-driven hyperparameter tuning. / Shishehgarkhaneh, Milad Baghalzadeh; Chan, Melissa; Moehler, Robert C. et al.
International Conference on Electrical, Computer, and Energy Technologies (ICECET 2024), 25th - 27th July, 2024, Sydney, Australia. U.S.: IEEE, 2024.

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

TY - GEN

T1 - Named entity recognition in construction supply chain risk management using transformer-based models and genetic algorithm-driven hyperparameter tuning

AU - Shishehgarkhaneh, Milad Baghalzadeh

AU - Chan, Melissa

AU - Moehler, Robert C.

AU - Fang, Yihai

AU - Hijazi, Amer A.

AU - Aboutorab, Hamed

N1 - Conference code: 4th

PY - 2024

Y1 - 2024

N2 - The construction industry faces significant supply chain risks, necessitating effective management strategies. This paper presents a novel approach using transformer-based models for Named Entity Recognition (NER) to identify risk-related entities within construction supply chain management (SCRM) from news articles. It specifically explores the efficacy of two transformer models, BERT and DeBERTa, and employs Genetic Algorithms (GAs) for optimizing model hyperparameters. This research underscores the transformative potential of NLP-driven solutions in enhancing SCRM, particularly within the unique context of the Australian construction industry. The findings highlight the importance of precision in entity recognition for effective SCRM and demonstrate the superiority of DeBERTa in precision-focused tasks, making it a promising tool for practitioners in this field.

AB - The construction industry faces significant supply chain risks, necessitating effective management strategies. This paper presents a novel approach using transformer-based models for Named Entity Recognition (NER) to identify risk-related entities within construction supply chain management (SCRM) from news articles. It specifically explores the efficacy of two transformer models, BERT and DeBERTa, and employs Genetic Algorithms (GAs) for optimizing model hyperparameters. This research underscores the transformative potential of NLP-driven solutions in enhancing SCRM, particularly within the unique context of the Australian construction industry. The findings highlight the importance of precision in entity recognition for effective SCRM and demonstrate the superiority of DeBERTa in precision-focused tasks, making it a promising tool for practitioners in this field.

KW - BERT

KW - Construction Supply Chain

KW - Genetic Algorithms

KW - Proactive Risk Management

KW - Transformer Models

UR - http://www.scopus.com/inward/record.url?scp=85207451101&partnerID=8YFLogxK

UR - https://go.openathens.net/redirector/westernsydney.edu.au?url=https://doi.org/10.1109/ICECET61485.2024.10698305

U2 - 10.1109/ICECET61485.2024.10698305

DO - 10.1109/ICECET61485.2024.10698305

M3 - Conference Paper

AN - SCOPUS:85207451101

BT - International Conference on Electrical, Computer, and Energy Technologies (ICECET 2024), 25th - 27th July, 2024, Sydney, Australia

PB - IEEE

CY - U.S.

T2 - International Conference on Electrical, Computer, and Energy Technologies

Y2 - 25 July 2024 through 27 July 2024

ER -

Shishehgarkhaneh MB, Chan M, Moehler RC, Fang Y, Hijazi AA, Aboutorab H. Named entity recognition in construction supply chain risk management using transformer-based models and genetic algorithm-driven hyperparameter tuning. In International Conference on Electrical, Computer, and Energy Technologies (ICECET 2024), 25th - 27th July, 2024, Sydney, Australia. U.S.: IEEE. 2024 doi: 10.1109/ICECET61485.2024.10698305

Named entity recognition in construction supply chain risk management using transformer-based models and genetic algorithm-driven hyperparameter tuning

Abstract

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this