TY - GEN
T1 - Event Extraction for aviation accident reports through attention-based multi-label classification
AU - Zhao, Xinyu
AU - Yan, Hao
AU - Liu, Yongming
N1 - Publisher Copyright:
© 2022, American Institute of Aeronautics and Astronautics Inc, AIAA. All rights reserved.
PY - 2022
Y1 - 2022
N2 - In the aviation domain, historical aviation accidents are recorded to prevent catastrophe in the future. The national transportation safety board (NTSB) provides a large volume of accident reports and designs aviation event taxonomy to summarize what happens during the accidents. By utilizing the event taxonomy, we are able to design tools to analyze the accident reports, such as information retrieval systems, fault tree analysis, and causal chain analysis. However, one of the challenges is how to appropriately identify the accident reports with those event taxonomies. Traditionally, domain experts will label those events manually, which is time-consuming and subjective. In this paper, we propose the formulate the event labeling task as a sequence generation task. By adopting an advanced sequence generation framework, our experiment results show that we can achieve promising results on those frequent events.
AB - In the aviation domain, historical aviation accidents are recorded to prevent catastrophe in the future. The national transportation safety board (NTSB) provides a large volume of accident reports and designs aviation event taxonomy to summarize what happens during the accidents. By utilizing the event taxonomy, we are able to design tools to analyze the accident reports, such as information retrieval systems, fault tree analysis, and causal chain analysis. However, one of the challenges is how to appropriately identify the accident reports with those event taxonomies. Traditionally, domain experts will label those events manually, which is time-consuming and subjective. In this paper, we propose the formulate the event labeling task as a sequence generation task. By adopting an advanced sequence generation framework, our experiment results show that we can achieve promising results on those frequent events.
UR - http://www.scopus.com/inward/record.url?scp=85135376994&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85135376994&partnerID=8YFLogxK
U2 - 10.2514/6.2022-3831
DO - 10.2514/6.2022-3831
M3 - Conference contribution
AN - SCOPUS:85135376994
SN - 9781624106354
T3 - AIAA AVIATION 2022 Forum
BT - AIAA AVIATION 2022 Forum
PB - American Institute of Aeronautics and Astronautics Inc, AIAA
T2 - AIAA AVIATION 2022 Forum
Y2 - 27 June 2022 through 1 July 2022
ER -