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

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

Research output: Book chapter/Published conference paperConference paperpeer-review

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 languageEnglish
Title of host publicationInternational Conference on Electrical, Computer, and Energy Technologies, ICECET 2024
PublisherIEEE, Institute of Electrical and Electronics Engineers
Number of pages7
ISBN (Electronic)9798350395914
ISBN (Print)9798350395921
DOIs
Publication statusPublished - 2024
Event4th IEEE International Conference on Electrical, Computer, and Energy Technologies, ICECET 2024: ICECET 2024 - Radisson Blu Plaza Hotel, Sydney, Australia
Duration: 25 Jul 202427 Jul 2024
https://www.icecet.com/2024/
https://web.archive.org/web/20240726045804/https://www.icecet.com/prg_p.pdf (Program)
https://web.archive.org/web/20240725171923/https://www.icecet.com/prg_o.pdf (Online program)
https://ieeexplore-ieee-org.ezproxy.csu.edu.au/xpl/conhome/10697983/proceeding (Proceedings)

Publication series

NameInternational Conference on Electrical, Computer, and Energy Technologies, ICECET 2024

Conference

Conference4th IEEE International Conference on Electrical, Computer, and Energy Technologies, ICECET 2024
Country/TerritoryAustralia
CitySydney
Period25/07/2427/07/24
OtherThe 4th International Conference on Electrical, Computer and Energy Technologies (ICECET) is a multidisciplinary, peer-reviewed international conference that provides a forum for the exchange of latest technical information, the dissemination of the high-quality research results, the presentation of the new developments in the area, and the debate and shaping of future directions and priorities. ICECET aims to bring together leading academic scientists, researchers and research scholars to exchange and share their experiences and research results on all aspects of Electrical, Computer and Energy Technologies.
Internet address

Fingerprint

Dive into the research topics of 'Named entity recognition in construction supply chain risk management using transformer-based models and genetic algorithm-driven hyper-parameter tuning'. Together they form a unique fingerprint.

Cite this