TY - GEN
T1 - Similarity analysis of terminologies in standards
T2 - 29th European Safety and Reliability Conference, ESREL 2019
AU - Meng, Huixing
AU - Setthapitayakul, Kanittha
AU - Li, Yan Fu
N1 - Publisher Copyright:
© 2019 European Safety and Reliability Association. Published by Research Publishing, Singapore.
PY - 2020
Y1 - 2020
N2 - The application of standards is effective for ensuring expected performance of a system in specific scenarios. A key step of standard enaction or implementation is to precisely comprehend standard terminologies via literal comparison. Current methods for such comparison usually rely heavily on labor, which is usually time-consuming and error-prone. With the rapid increase of the number of standard documents, it is essential to develop an approach to automatize the comparison process. In this work, we proposed a methodology for computerized comparison of terms and definitions in standards. The methodology is comprised of three steps: extraction of portable document format (PDF) text, extraction of terms and definitions, and comparison of definitions. (1) According to PDF types, either scanned or digitally created, corresponding methods are provided for converting PDF documents. (2) Regarding terms and definitions extraction, we identified content structures and logical elements and extracted definition sections and terms. (3) Concerning the comparison step, we evaluated terminology similarities from semantic and syntactic aspects. Reliability, availability, maintainability, and safety (RAMS) are crucial attributes to evaluate system performance. In experimental studies, we compared several RAMS standards issued by IEC, IEEE, ISO, and the Society for Automotive Engineering (SAE). The results show that the applied methodology is capable of evaluating similarities of terms and definitions in standards.
AB - The application of standards is effective for ensuring expected performance of a system in specific scenarios. A key step of standard enaction or implementation is to precisely comprehend standard terminologies via literal comparison. Current methods for such comparison usually rely heavily on labor, which is usually time-consuming and error-prone. With the rapid increase of the number of standard documents, it is essential to develop an approach to automatize the comparison process. In this work, we proposed a methodology for computerized comparison of terms and definitions in standards. The methodology is comprised of three steps: extraction of portable document format (PDF) text, extraction of terms and definitions, and comparison of definitions. (1) According to PDF types, either scanned or digitally created, corresponding methods are provided for converting PDF documents. (2) Regarding terms and definitions extraction, we identified content structures and logical elements and extracted definition sections and terms. (3) Concerning the comparison step, we evaluated terminology similarities from semantic and syntactic aspects. Reliability, availability, maintainability, and safety (RAMS) are crucial attributes to evaluate system performance. In experimental studies, we compared several RAMS standards issued by IEC, IEEE, ISO, and the Society for Automotive Engineering (SAE). The results show that the applied methodology is capable of evaluating similarities of terms and definitions in standards.
KW - Definitions
KW - Extraction
KW - RAMS
KW - Standards
KW - Terms
KW - Text extraction
UR - http://www.scopus.com/inward/record.url?scp=85089180203&partnerID=8YFLogxK
U2 - 10.3850/978-981-11-2724-3_0073-cd
DO - 10.3850/978-981-11-2724-3_0073-cd
M3 - Conference contribution
AN - SCOPUS:85089180203
T3 - Proceedings of the 29th European Safety and Reliability Conference, ESREL 2019
SP - 3001
EP - 3008
BT - Proceedings of the 29th European Safety and Reliability Conference, ESREL 2019
A2 - Beer, Michael
A2 - Zio, Enrico
PB - Research Publishing Services
Y2 - 22 September 2019 through 26 September 2019
ER -