Market research for requirements analysis using linguistic tools

Mich, Luisa; Franch, Mariangela; Inverardi, Luigi Novi

doi:10.1007/s00766-004-0195-3

Cited by 126 publications

(80 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Among the leading causes of such a staggering increase in the number of requirements we find: the ever-increasing complexity of products and their relentless customisation; the mushrooming accumulation of legal documents; and the geographically dispersed teams through whom products are developed. In addition, requirements are scattered in unstructured prescriptive documents -e.g., Word, PDF, Excel -and a majority -79% according to Mich et al (2004) -are written in unrestricted natural language.…”

Section: Problemmentioning

confidence: 99%

Requirement mining for model-based product design

Croué¹,

Véron

Segonds

et al. 2016

IJPLM

View full text Add to dashboard Cite

PLM software applications should enable engineers to develop and manage requirements throughout the product's lifecycle. However, PLM activities of the beginning-of-life and end-of-life of a product mainly deal with a fastidious document-based approach. Indeed, requirements are scattered in many different prescriptive documents (reports, specifications, standards, regulations, etc.) that make the feeding of a requirements management tool laborious. Our contribution is two-fold. First, we propose a natural language processing (NLP) pipeline to extract requirements from prescriptive documents. Second, we show how machine learning techniques can be used to develop a text classifier that will automatically classify requirements into disciplines. Both contributions support companies willing to feed a requirements management tool from prescriptive documents. The NLP experiment shows an average precision of 0.86 and an average recall of 0.95, whereas the SVM requirements classifier outperforms that of naive Bayes with a 76% accuracy rate.Keywords: requirements; unstructured; extraction; classification; natural language processing; NLP; supervised learning; machine learning. 306 R. Pinquié et al.Reference to this paper should be made as follows: Pinquié, R., Véron, R., Segonds, F. and Croué, N. (2016) Frédéric Segonds is an Assistant Professor at Arts et Metiers ParisTech and member of the Product Design and Innovation Laboratory (LCPI). His research interests focus on the early stages of design collaboration, optimisation and collaborative design. This area includes the integration of stakeholders' core competences into the early stages of design, and providing methodologies and tools to support early product design.Nicolas Croué is the Solutions and Consulting Director for the company Keonys and has responsibility for developing business and technical activities in a range of domains including simulation, systems engineering, search-based applications, business intelligence and manufacturing so as to develop solutions for the factory of the future. After graduating from the ESILV in Mechanical and Systems Engineering, he successfully worked for the Petroleum French Institute, SAMTECH and LMS and became an expert in systems engineering. This paper is a revised and expanded version of a paper entitled 'Natural language processing of requirements for model-based product design with ENOVIA/CATIA

show abstract

Section: Problemmentioning

confidence: 99%

Requirement mining for model-based product design

Croué¹,

Véron

Segonds

et al. 2016

IJPLM

View full text Add to dashboard Cite

show abstract

“…There is research concerning the automatic translation of natural language requirements into behavioral models to support the automation of system and acceptance testing (see e.g. [8]) but it is not widely adopted in industrial practice [9]. Formal mathematical methods may be used to express requirements, but their application requires high expertise and, hence, they are not very common in industrial practice.…”

Section: Objectivesmentioning

confidence: 99%

“…[10]. The bottom line is that natural language is still the most common approach to express requirements in practice [9]. We want to provide a solution to the question of how to formalize requirements so that they can be processed and evaluated during system simulations in order to detect errors or inconsistencies in a way that is easy to understand and to apply.…”

Section: Objectivesmentioning

confidence: 99%

Virtual Verification of System Designs against System Requirements

Schamai¹,

Helle²,

Fritzson

et al. 2011

Models in Software Engineering

View full text Add to dashboard Cite

Abstract. System development and integration with a sufficient maturity at entry into service is a competitive challenge in the aerospace sector. With the ever-increasing complexity of products, this can only be achieved using efficient model-based techniques for system design as well as for system testing. However, natural language requirements engineering is an established technique that cannot be completely replaced for a number of reasons. This is a fact that has to be considered by any new approach. Building on the general idea of model-based systems engineering, we aim at building an integrated virtual verification environment for modeling systems, requirements, and test cases, so that system designs can be simulated and verified against the requirements in the early stages of system development. This paper provides a description of the virtual verification of system designs against system requirements methodology and exemplifies its application in a ModelicaML modeling environment.

show abstract

“…That's why the natural language is widely used in industry to state requirements for all types of systems, because it is flexible and universal. A recent study shows that several software development companies use common natural language for specifying requirements in the early phases [27]. Although documents written in natural language are often hard to process automatically and inconsistency is difficult to detect, NLP techniques and tools [1; 10] can be used to extract template-relevant meaning from the stakeholder expectations to achieve a higher level of understanding.…”

Section: Gap-bridging Approachesmentioning

confidence: 99%