SNOWTEC: Synthetic Natural language Oversampling With Transformer-based information ExtraCtion for automated compliance checking

Hettiarachchi, Hansi and Gaber, Mohamed Medhat and Parsafard, Pouyan and Vakaj, Edlira (2026) SNOWTEC: Synthetic Natural language Oversampling With Transformer-based information ExtraCtion for automated compliance checking. Machine Learning with Applications, 24. p. 100911. ISSN 2666-8270

Preview

Text 1-s2.0-S2666827026000769-main.pdf - Published Version Available under License Creative Commons Attribution. Download (3MB)

Abstract

The optimisation of Automated Compliance Checking (ACC) in Architecture, Engineering, and Construction (AEC) necessitates the interpretation of building codes into machine-processable formats. As these codes primarily exist in textual form, Information Extraction (IE) became integral to decoding this data, encouraging various IE techniques spanning manual, rule-based, and machine-learning methodologies. Recent research has shown promise in adopting deep learning; however, as far as we know, within AEC, the transformers/language models’ potential remains untapped/unexplored, yet they hold state-of-the-art performance across various text-based tasks. To address this gap, we propose an approach based on Synthetic Natural language Oversampling With Transformer-based information ExtraCtion (SNOWTEC), designed to extract entities and relations from regulatory text to convert them into machine-processable knowledge graphs. We involve transformer-based architectures and introduce an innovative data oversampling/augmentation approach addressing data scarcity, which impedes model performance. Our experiments across multiple sub-domains highlight the transformers’ strength in identifying relations but also reveal challenges in recognising entities within the AEC domain, providing insights for future research. Data oversampling played a crucial role in improving relation extraction, resulting in a notable 26% average F1 increase.

Item Type:	Article
Identification Number:	10.1016/j.mlwa.2026.100911
Dates:	Date Event 24 April 2026 Accepted 5 May 2026 Published Online
Uncontrolled Keywords:	Automated compliance checking, Information extraction, Entity-relation knowledge graphs, Transformers, Deep learning, Data augmentation
Subjects:	CAH11 - computing > CAH11-01 - computing > CAH11-01-01 - computer science
Divisions:	Architecture, Built Environment, Computing and Engineering > Computer Science
Depositing User:	Gemma Tonks
Date Deposited:	10 Nov 2026 15:04
Last Modified:	10 Nov 2026 15:04
URI:	https://www.open-access.bcu.ac.uk/id/eprint/17305

Actions (login required)

View Item