Aviation-BERT-NER: Named Entity Recognition for Aviation Safety Reports
Aerospace · 29.10.2024 · 11 (11) · 890
DOI: 10.3390/aerospace11110890 ↗Kurz gefasst
Fachartikel in der Zeitschrift Aerospace, online erschienen am 29.10.2024. Verfasst von Chetan Chandra und 3 weiteren Autor:innen. Die Arbeit wurde bisher 23-mal zitiert (Crossref) und nennt 47 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: U.S. Federal Aviation Administration (FAA).
Abstract (Originalsprache)
This work introduces Aviation-BERT-NER, a Named Entity Recognition (NER) system tailored for aviation safety reports, building on the Aviation-BERT base model developed at the Georgia Institute of Technology’s Aerospace Systems Design Laboratory. This system integrates aviation domain-specific data, including aircraft types, manufacturers, quantities, and aviation terminology, to identify named entities critical for aviation safety analysis. A key innovation of Aviation-BERT-NER is its template-based approach to fine-tuning, which utilizes structured datasets to generate synthetic training data that mirror the complexity of real-world aviation safety reports. This method significantly improves the model’s generalizability and adaptability, enabling rapid updates and customization to meet evolving domain-specific requirements. The development process involved careful data preparation, including the synthesis of entity types and the generation of labeled datasets through template filling. Testing on real-world narratives from the National Transportation Safety Board (NTSB) database highlighted Aviation-BERT-NER’s robustness, with a precision of 95.34%, recall of 94.62%, and F1 score of 94.78% when evaluated over 50 manually annotated (BIO tagged) paragraphs. This work addresses a critical gap in English language NER models for aviation safety, promising substantial improvements in the analysis and understanding of aviation safety reports.
Förderung
- U.S. Federal Aviation Administration (FAA)
Zitieren
APA
Chandra, C., Ojima, Y., Bendarkar, M. V., & Mavris, D. N. (2024). Aviation-BERT-NER: Named Entity Recognition for Aviation Safety Reports. Aerospace, 11(11), 890. https://doi.org/10.3390/aerospace11110890
Vancouver
Chandra C, Ojima Y, Bendarkar MV, Mavris DN. Aviation-BERT-NER: Named Entity Recognition for Aviation Safety Reports. Aerospace. 2024;11(11):890. doi:10.3390/aerospace11110890
BibTeX
@article{Chandra2024,
author = {Chandra, Chetan and Ojima, Yuga and Bendarkar, Mayank V. and Mavris, Dimitri N.},
title = {Aviation-BERT-NER: Named Entity Recognition for Aviation Safety Reports},
journal = {Aerospace},
year = {2024},
volume = {11},
number = {11},
pages = {890},
doi = {10.3390/aerospace11110890}
}
EUVIMED