Automatic knowledge extraction from industrial maintenance short text using deep learning

Tyler Bikaun

doi:10.26182/hhg8-ra38

Automatic knowledge extraction from industrial maintenance short text using deep learning

Tyler Bikaun

School of Physics, Mathematics and Computing

Research output: Thesis › Doctoral Thesis

32 Downloads (Pure)

Abstract

This thesis addresses the challenges of extracting valuable information from maintenance work order records and their short texts using Natural Language Processing. It introduces new tools - LexiClean and QuickGraph - for annotating maintenance texts, along with language resources MaintNorm, MaintIE, and MaintNormIE for lexical normalisation and information extraction. The research proposes a method for automatically constructing knowledge graphs from these records to capture both explicit and implicit domain knowledge, enabling domain experts to effectively query and analyse maintenance records. This work advances both NLP applications in industrial maintenance and practical insights extraction for better asset management.

Original language	English
Qualification	Doctor of Philosophy
Awarding Institution	The University of Western Australia
Supervisors/Advisors	Liu, Wei, Supervisor French, Tim, Supervisor Hodkiewicz, Melinda, Supervisor Stewart, Michael, Supervisor
Thesis sponsors	Australian Government Research Training Program
Award date	19 May 2025
DOIs	https://doi.org/10.26182/hhg8-ra38
Publication status	Unpublished - 2024

Access to Document

10.26182/hhg8-ra38

THESIS - DOCTOR OF PHILOSOPHY - BIKAUN Tyler Ken - 2024
This work is protected by Copyright. You may print or download ONE copy of this document for the purpose of your own non-commercial research or study. Any other use requires permission from the copyright owner. The Copyright Act requires you to attribute any copyright works you quote or paraphrase.

4 Conference paper

MaintIE: A Fine-Grained Annotation Schema and Benchmark for Information Extraction from Maintenance Short Texts.
Bikaun, T. K., French, T., Stewart, M., Liu, W. & Hodkiewicz, M., 2024, 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation, LREC-COLING 2024 - Main Conference Proceedings: Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024). Calzolari, N., Kan, M.-Y., Hoste, V., Lenci, A., Sakti, S. & Xue, N. (eds.). Association for Computational Linguistics (ACL), p. 10939-10951 13 p. (2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation, LREC-COLING 2024 - Main Conference Proceedings).
Research output: Chapter in Book/Conference paper › Conference paper › peer-review

Open Access
File
MaintNorm: A corpus and benchmark model for lexical normalisation and masking of industrial maintenance short text
Bikaun, T., Hodkiewicz, M. & Liu, W., 2024, W-NUT 2024 - 9th Workshop on Noisy and User-Generated Text, Proceedings of the Workshop. van der Goot, R., Bak, J., Muller-Eberstein, M., Xu, W., Ritter, A., Baldwin, T. & Baldwin, T. (eds.). Association for Computational Linguistics (ACL), p. 58-67 10 p. (W-NUT 2024 - 9th Workshop on Noisy and User-Generated Text, Proceedings of the Workshop).
Research output: Chapter in Book/Conference paper › Conference paper › peer-review
QuickGraph: A Rapid Annotation Tool for Knowledge Graph Extraction from Technical Text
Bikaun, T., Stewart, M. & Liu, W., 2022, Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics: System Demonstrations. Basile, V., Kozareva, Z. & Stajner, S. (eds.). USA: Association for Computational Linguistics (ACL), p. 270-278 9 p. (Proceedings of the Annual Meeting of the Association for Computational Linguistics).
Research output: Chapter in Book/Conference paper › Conference paper › peer-review

Open Access
13 Citations (Scopus)

Cite this

@phdthesis{b7adee303efc4e20a219ae32a2c02007,

title = "Automatic knowledge extraction from industrial maintenance short text using deep learning",

abstract = "This thesis addresses the challenges of extracting valuable information from maintenance work order records and their short texts using Natural Language Processing. It introduces new tools - LexiClean and QuickGraph - for annotating maintenance texts, along with language resources MaintNorm, MaintIE, and MaintNormIE for lexical normalisation and information extraction. The research proposes a method for automatically constructing knowledge graphs from these records to capture both explicit and implicit domain knowledge, enabling domain experts to effectively query and analyse maintenance records. This work advances both NLP applications in industrial maintenance and practical insights extraction for better asset management.",

keywords = "natural language processing, maintenance, knowledge graphs, lexical normalisation, annotation tools",

author = "Tyler Bikaun",

year = "2024",

doi = "10.26182/hhg8-ra38",

language = "English",

school = "The University of Western Australia",

}

TY - BOOK

T1 - Automatic knowledge extraction from industrial maintenance short text using deep learning

AU - Bikaun, Tyler

PY - 2024

Y1 - 2024

N2 - This thesis addresses the challenges of extracting valuable information from maintenance work order records and their short texts using Natural Language Processing. It introduces new tools - LexiClean and QuickGraph - for annotating maintenance texts, along with language resources MaintNorm, MaintIE, and MaintNormIE for lexical normalisation and information extraction. The research proposes a method for automatically constructing knowledge graphs from these records to capture both explicit and implicit domain knowledge, enabling domain experts to effectively query and analyse maintenance records. This work advances both NLP applications in industrial maintenance and practical insights extraction for better asset management.

AB - This thesis addresses the challenges of extracting valuable information from maintenance work order records and their short texts using Natural Language Processing. It introduces new tools - LexiClean and QuickGraph - for annotating maintenance texts, along with language resources MaintNorm, MaintIE, and MaintNormIE for lexical normalisation and information extraction. The research proposes a method for automatically constructing knowledge graphs from these records to capture both explicit and implicit domain knowledge, enabling domain experts to effectively query and analyse maintenance records. This work advances both NLP applications in industrial maintenance and practical insights extraction for better asset management.

KW - natural language processing

KW - maintenance

KW - knowledge graphs

KW - lexical normalisation

KW - annotation tools

U2 - 10.26182/hhg8-ra38

DO - 10.26182/hhg8-ra38

M3 - Doctoral Thesis

ER -

Automatic knowledge extraction from industrial maintenance short text using deep learning

Abstract

Access to Document

Fingerprint

Research output

MaintIE: A Fine-Grained Annotation Schema and Benchmark for Information Extraction from Maintenance Short Texts.

MaintNorm: A corpus and benchmark model for lexical normalisation and masking of industrial maintenance short text

QuickGraph: A Rapid Annotation Tool for Knowledge Graph Extraction from Technical Text

Cite this