Agile Methodology for the Standardization of Engineering Requirements Using Large Language Models

被引:8
作者
Ray, Archana Tikayat [1 ]
Cole, Bjorn F. [2 ]
Fischer, Olivia Pinon J. [1 ]
Bhat, Anirudh Prabhakara [3 ]
White, Ryan T. [4 ]
Mavris, Dimitri N. [1 ]
机构
[1] Georgia Inst Technol, Sch Aerosp Engn, Aerosp Syst Design Lab, Atlanta, GA 30332 USA
[2] Lockheed Martin Space, Littleton, CO 80127 USA
[3] Amazon, Toronto, ON M5H 4A9, Canada
[4] Florida Inst Technol, Dept Math Sci, Neural Transmiss Lab, Melbourne, FL 32901 USA
来源
SYSTEMS | 2023年 / 11卷 / 07期
关键词
requirements engineering; Large Language Models (LLMs); transformer-based language models; Natural Language Processing (NLP); BERT; requirement boilerplates; model-based systems engineering; requirement tables;
D O I
10.3390/systems11070352
中图分类号
C [社会科学总论];
学科分类号
03 ; 0303 ;
摘要
The increased complexity of modern systems is calling for an integrated and comprehensive approach to system design and development and, in particular, a shift toward Model-Based Systems Engineering (MBSE) approaches for system design. The requirements that serve as the foundation for these intricate systems are still primarily expressed in Natural Language (NL), which can contain ambiguities and inconsistencies and suffer from a lack of structure that hinders their direct translation into models. The colossal developments in the field of Natural Language Processing (NLP), in general, and Large Language Models (LLMs), in particular, can serve as an enabler for the conversion of NL requirements into machine-readable requirements. Doing so is expected to facilitate their standardization and use in a model-based environment. This paper discusses a two-fold strategy for converting NL requirements into machine-readable requirements using language models. The first approach involves creating a requirements table by extracting information from free-form NL requirements. The second approach consists of an agile methodology that facilitates the identification of boilerplate templates for different types of requirements based on observed linguistic patterns. For this study, three different LLMs are utilized. Two of these models are fine-tuned versions of Bidirectional Encoder Representations from Transformers (BERTs), specifically, aeroBERT-NER and aeroBERT-Classifier, which are trained on annotated aerospace corpora. Another LLM, called flair/chunk-english, is utilized to identify sentence chunks present in NL requirements. All three language models are utilized together to achieve the standardization of requirements. The effectiveness of the methodologies is demonstrated through the semi-automated creation of boilerplates for requirements from Parts 23 and 25 of Title 14 Code of Federal Regulations (CFRs).
引用
收藏
页数:28
相关论文
共 39 条
[21]  
Jacobson L, 2021, UNIFIED MODELING LAN
[22]  
Jurafsky D., 2021, SPEECH LANGUAGE PROC
[23]   An MBSE Approach to Pass from Requirements to Functional Architecture [J].
Lemazurier, L. ;
Chapurlat, V. ;
Grossetete, A. .
IFAC PAPERSONLINE, 2017, 50 (01) :7260-7265
[24]   EARS (Easy Approach to Requirements Syntax) [J].
Mavin, Alistair ;
Wilkinson, Philip ;
Harwood, Adrian ;
Novak, Mark .
PROCEEDINGS OF THE 2009 17TH IEEE INTERNATIONAL REQUIREMENTS ENGINEERING CONFERENCE, 2009, :317-322
[25]  
Mazo R., 2020, J SOFTW ENG RES DEV, V8, P3, DOI [10.5753/jserd.2020.473, DOI 10.5753/JSERD.2020.473]
[26]  
NASA Appendix C, WRIT GOOD REQ, P115
[27]  
nomagic, REQ TABL
[28]  
Radford Alec, 2019, OpenAI blog, V1, P9
[29]  
Raffel C, 2020, J MACH LEARN RES, V21
[30]  
Ray A.T., 2023, P AIAA SCITECH 2023, DOI DOI 10.2514/6.2023-2583