A deep neural network-based method for deep information extraction using transfer learning strategies to support automated compliance checking

Existing automated compliance checking (ACC) systems require the extraction of requirements from regulatory documents into computer-processable representations. These information extraction (IE) processes are either fully manual, semi-automated, or automated. Semi-automated and manual approaches typ...

Full description

Saved in:
Bibliographic Details
Published in:Automation in construction 2021-12, Vol.132, p.103834, Article 103834
Main Authors: Zhang, Ruichuan, El-Gohary, Nora
Format: Article
Language:English
Subjects:
Annotations
Artificial neural networks
Automation
Code checking
Deep learning
Domains
Information extraction
Information retrieval
Machine learning
Neural networks
Transfer learning
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Existing automated compliance checking (ACC) systems require the extraction of requirements from regulatory documents into computer-processable representations. These information extraction (IE) processes are either fully manual, semi-automated, or automated. Semi-automated and manual approaches typically use manual annotations or predefined IE rules, which lack sufficient flexibility and scalability; the annotations and rules typically need adaptation if the characteristics of the regulatory document change. There is, thus, a need for a fully automated IE approach that can achieve high and consistent performance across different types of regulatory documents for supporting ACC. To address this need, this paper proposes a deep neural network-based method for deep IE – extracting semantic and syntactic information elements – from regulatory documents in the architectural, engineering, and construction (AEC) domain. The proposed method was evaluated in extracting information from multiple regulatory documents in the AEC domain. It achieved average precision and recall of 93.1% and 92.9%, respectively. •Deep information extraction from building codes to support automated code checking.•Proposed syntactic and semantic information elements to represent requirements.•A deep learning model to extract regulatory information.•Transfer learning strategies to leverage existing labeled text data.•Good information extraction performance across different types of building codes.
ISSN:0926-5805
1872-7891
DOI:10.1016/j.autcon.2021.103834