skip to main content
OSTI.GOV title logo U.S. Department of Energy
Office of Scientific and Technical Information

Title: Extracting Information from Narratives: An Application to Aviation Safety Reports

Abstract

Aviation safety reports are the best available source of information about why a flight incident happened. However, stream of consciousness permeates the narratives making difficult the automation of the information extraction task. We propose an approach and infrastructure based on a common pattern specification language to capture relevant information via normalized template expression matching in context. Template expression matching handles variants of multi-word expressions. Normalization improves the likelihood of correct hits by standardizing and cleaning the vocabulary used in narratives. Checking for the presence of negative modifiers in the proximity of a potential hit reduces the chance of false hits. We present the above approach in the context of a specific application, which is the extraction of human performance factors from NASA ASRS reports. While knowledge infusion from experts plays a critical role during the learning phase, early results show that in a production mode, the automated process provides information that is consistent with analyses by human subjects.

Authors:
; ; ; ; ;
Publication Date:
Research Org.:
Pacific Northwest National Lab. (PNNL), Richland, WA (United States)
Sponsoring Org.:
USDOE
OSTI Identifier:
877017
Report Number(s):
PNWD-SA-6702
TRN: US200608%%249
DOE Contract Number:  
AC05-76RL01830
Resource Type:
Conference
Resource Relation:
Conference: 2005 IEEE Aerospace Conference, 1-14
Country of Publication:
United States
Language:
English
Subject:
99 GENERAL AND MISCELLANEOUS//MATHEMATICS, COMPUTING, AND INFORMATION SCIENCE; AIRCRAFT; SAFETY REPORTS; INFORMATION RETRIEVAL; AUTOMATION; PERFORMANCE; PERSONNEL; statistics; aviation safety; language analysis

Citation Formats

Posse, Christian, Matzke, Brett D., Anderson, Catherine M., Brothers, Alan J., Matzke, Melissa M., and Ferryman, Thomas A. Extracting Information from Narratives: An Application to Aviation Safety Reports. United States: N. p., 2005. Web.
Posse, Christian, Matzke, Brett D., Anderson, Catherine M., Brothers, Alan J., Matzke, Melissa M., & Ferryman, Thomas A. Extracting Information from Narratives: An Application to Aviation Safety Reports. United States.
Posse, Christian, Matzke, Brett D., Anderson, Catherine M., Brothers, Alan J., Matzke, Melissa M., and Ferryman, Thomas A. Thu . "Extracting Information from Narratives: An Application to Aviation Safety Reports". United States.
@article{osti_877017,
title = {Extracting Information from Narratives: An Application to Aviation Safety Reports},
author = {Posse, Christian and Matzke, Brett D. and Anderson, Catherine M. and Brothers, Alan J. and Matzke, Melissa M. and Ferryman, Thomas A.},
abstractNote = {Aviation safety reports are the best available source of information about why a flight incident happened. However, stream of consciousness permeates the narratives making difficult the automation of the information extraction task. We propose an approach and infrastructure based on a common pattern specification language to capture relevant information via normalized template expression matching in context. Template expression matching handles variants of multi-word expressions. Normalization improves the likelihood of correct hits by standardizing and cleaning the vocabulary used in narratives. Checking for the presence of negative modifiers in the proximity of a potential hit reduces the chance of false hits. We present the above approach in the context of a specific application, which is the extraction of human performance factors from NASA ASRS reports. While knowledge infusion from experts plays a critical role during the learning phase, early results show that in a production mode, the automated process provides information that is consistent with analyses by human subjects.},
doi = {},
journal = {},
number = ,
volume = ,
place = {United States},
year = {Thu May 12 00:00:00 EDT 2005},
month = {Thu May 12 00:00:00 EDT 2005}
}

Conference:
Other availability
Please see Document Availability for additional information on obtaining the full-text document. Library patrons may search WorldCat to identify libraries that hold this conference proceeding.

Save / Share: