Feature Extraction from Japanese Natural Language Requirements Documents for Software Product Line Engineering

研究成果: 著書/レポートタイプへの貢献会議での発言

抄録

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.

元の言語英語
ホスト出版物のタイトルProceedings - Companion of the 19th IEEE International Conference on Software Quality, Reliability and Security, QRS-C 2019
出版者Institute of Electrical and Electronics Engineers Inc.
ページ322-329
ページ数8
ISBN(電子版)9781728139258
DOI
出版物ステータス出版済み - 7 2019
イベント19th IEEE International Conference on Software Quality, Reliability and Security Companion, QRS-C 2019 - Sofia, ブルガリア
継続期間: 7 22 20197 26 2019

出版物シリーズ

名前Proceedings - Companion of the 19th IEEE International Conference on Software Quality, Reliability and Security, QRS-C 2019

会議

会議19th IEEE International Conference on Software Quality, Reliability and Security Companion, QRS-C 2019
ブルガリア
Sofia
期間7/22/197/26/19

Fingerprint

Feature extraction
ranking
candidacy
engineering
Specifications
language
performance
Processing
software
time

All Science Journal Classification (ASJC) codes

  • Safety, Risk, Reliability and Quality
  • Law
  • Artificial Intelligence
  • Computer Networks and Communications
  • Software

これを引用

Hisazumi, K., Xiao, Y., & Fukuda, A. (2019). Feature Extraction from Japanese Natural Language Requirements Documents for Software Product Line Engineering. : Proceedings - Companion of the 19th IEEE International Conference on Software Quality, Reliability and Security, QRS-C 2019 (pp. 322-329). [8859423] (Proceedings - Companion of the 19th IEEE International Conference on Software Quality, Reliability and Security, QRS-C 2019). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/QRS-C.2019.00067

Feature Extraction from Japanese Natural Language Requirements Documents for Software Product Line Engineering. / Hisazumi, Kenji; Xiao, Yuedong; Fukuda, Akira.

Proceedings - Companion of the 19th IEEE International Conference on Software Quality, Reliability and Security, QRS-C 2019. Institute of Electrical and Electronics Engineers Inc., 2019. p. 322-329 8859423 (Proceedings - Companion of the 19th IEEE International Conference on Software Quality, Reliability and Security, QRS-C 2019).

研究成果: 著書/レポートタイプへの貢献会議での発言

Hisazumi, K, Xiao, Y & Fukuda, A 2019, Feature Extraction from Japanese Natural Language Requirements Documents for Software Product Line Engineering. : Proceedings - Companion of the 19th IEEE International Conference on Software Quality, Reliability and Security, QRS-C 2019., 8859423, Proceedings - Companion of the 19th IEEE International Conference on Software Quality, Reliability and Security, QRS-C 2019, Institute of Electrical and Electronics Engineers Inc., pp. 322-329, 19th IEEE International Conference on Software Quality, Reliability and Security Companion, QRS-C 2019, Sofia, ブルガリア, 7/22/19. https://doi.org/10.1109/QRS-C.2019.00067
Hisazumi K, Xiao Y, Fukuda A. Feature Extraction from Japanese Natural Language Requirements Documents for Software Product Line Engineering. : Proceedings - Companion of the 19th IEEE International Conference on Software Quality, Reliability and Security, QRS-C 2019. Institute of Electrical and Electronics Engineers Inc. 2019. p. 322-329. 8859423. (Proceedings - Companion of the 19th IEEE International Conference on Software Quality, Reliability and Security, QRS-C 2019). https://doi.org/10.1109/QRS-C.2019.00067
Hisazumi, Kenji ; Xiao, Yuedong ; Fukuda, Akira. / Feature Extraction from Japanese Natural Language Requirements Documents for Software Product Line Engineering. Proceedings - Companion of the 19th IEEE International Conference on Software Quality, Reliability and Security, QRS-C 2019. Institute of Electrical and Electronics Engineers Inc., 2019. pp. 322-329 (Proceedings - Companion of the 19th IEEE International Conference on Software Quality, Reliability and Security, QRS-C 2019).
@inproceedings{196e714591da4038bf28d12e81111f6d,
title = "Feature Extraction from Japanese Natural Language Requirements Documents for Software Product Line Engineering",
abstract = "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.",
author = "Kenji Hisazumi and Yuedong Xiao and Akira Fukuda",
year = "2019",
month = "7",
doi = "10.1109/QRS-C.2019.00067",
language = "English",
series = "Proceedings - Companion of the 19th IEEE International Conference on Software Quality, Reliability and Security, QRS-C 2019",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "322--329",
booktitle = "Proceedings - Companion of the 19th IEEE International Conference on Software Quality, Reliability and Security, QRS-C 2019",
address = "United States",

}

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

AN - SCOPUS:85073872793

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.

ER -