TY - GEN
T1 - Feature Extraction from Japanese Natural Language Requirements Documents for Software Product Line Engineering
AU - Hisazumi, Kenji
AU - Xiao, Yuedong
AU - Fukuda, Akira
PY - 2019/7
Y1 - 2019/7
N2 - Analyzing and extracting features from requirement specifications is an indispensable activity to support Software Product Line Engineering. However, performing features extraction is a time-consuming and inefficient task, since massive textual requirements need to be analyzed and classified. Most of the current approaches exhibited limitations: hindered applicability with requirements in Japanese; the support tools proposed were not made available publicly and thus making it hard for practitioners' adoption. This paper proposes a feature extraction approach from requirement specifications in Japanese using natural language processing techniques. Also, we propose a ranking method for extracted features to reduce efforts reviewing feature candidates. A case study was conducted to evaluate the performance of the proposed approach. Initial results show that 90.7% features were extracted correctly, and the top 40% features extracted contained 79.1% true features.
AB - Analyzing and extracting features from requirement specifications is an indispensable activity to support Software Product Line Engineering. However, performing features extraction is a time-consuming and inefficient task, since massive textual requirements need to be analyzed and classified. Most of the current approaches exhibited limitations: hindered applicability with requirements in Japanese; the support tools proposed were not made available publicly and thus making it hard for practitioners' adoption. This paper proposes a feature extraction approach from requirement specifications in Japanese using natural language processing techniques. Also, we propose a ranking method for extracted features to reduce efforts reviewing feature candidates. A case study was conducted to evaluate the performance of the proposed approach. Initial results show that 90.7% features were extracted correctly, and the top 40% features extracted contained 79.1% true features.
UR - http://www.scopus.com/inward/record.url?scp=85073872793&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85073872793&partnerID=8YFLogxK
U2 - 10.1109/QRS-C.2019.00067
DO - 10.1109/QRS-C.2019.00067
M3 - Conference contribution
T3 - Proceedings - Companion of the 19th IEEE International Conference on Software Quality, Reliability and Security, QRS-C 2019
SP - 322
EP - 329
BT - Proceedings - Companion of the 19th IEEE International Conference on Software Quality, Reliability and Security, QRS-C 2019
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 19th IEEE International Conference on Software Quality, Reliability and Security Companion, QRS-C 2019
Y2 - 22 July 2019 through 26 July 2019
ER -