From Requirements Engineering to UML using Natural Language Processing – Survey Study

Dawood, Omer Salih; Sahraoui, Abd‐El‐Kader

doi:10.24018/ejers.2017.2.1.236

Cited by 29 publications

(7 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…1 https://mde-network.com/ However, only limited future research direction and guidelines are provided in this work. Selected articles that generates UML diagram by applying NLP techniques are investigated in (Dawood et al, 2017;Abdelnabi et al, 2021). These works emphasize on immaturity of research area as most of the current processes are not automated.…”

Section: Related Workmentioning

confidence: 99%

Requirement Formalisation Using Natural Language Processing and Machine Learning: A Systematic Review

Kolahdouz-Rahimi

Lano

Lin

2023

Proceedings of the 11th International Conference on Model-Based Software and Systems Engineering

View full text Add to dashboard Cite

Improvement of software development methodologies attracts developers to automatic Requirement Formalisation (RF) in the Requirement Engineering (RE) field. The potential advantages by applying Natural Language Processing (NLP) and Machine Learning (ML) in reducing the ambiguity and incompleteness of requirement written in natural languages is reported in different studies. The goal of this paper is to survey and classify existing work on NLP and ML for RF, identifying challenges in this domain and providing promising future research directions. To achieve this, we conducted a systematic literature review to outline the current state-of-the-art of NLP and ML techniques in RF by selecting 257 papers from common used libraries. The search result is filtered by defining inclusion and exclusion criteria and 47 relevant studies between 2012 and 2022 are selected. We found that heuristic NLP approaches are the most common NLP techniques used for automatic RF, primary operating on structured and semi-structured data. This study also revealed that Deep Learning (DL) technique are not widely used, instead classical ML techniques are predominant in the surveyed studies. More importantly, we identified the difficulty of comparing the performance of different approaches due to the lack of standard benchmark cases for RF.

show abstract

Section: Related Workmentioning

confidence: 99%

Requirement Formalisation Using Natural Language Processing and Machine Learning: A Systematic Review

Kolahdouz-Rahimi

Lano

Lin

2023

Proceedings of the 11th International Conference on Model-Based Software and Systems Engineering

View full text Add to dashboard Cite

show abstract

“…The automation of UML diagram generation from natural language has seen progress, yet precision and recall challenges persist [13][14][15]. Studies by Dawood et al, Hossain and Rahman, More and Phalnikar, Arman and Jabbarin, and Maatuk and Abdelnabi present diverse NLP-based approaches for UML diagram generation [16][17][18][19][20].…”

Section: Automating Uml Diagrams Generationmentioning

confidence: 99%

Gunning Fog Index and Automated UML Generation

Djaber,

HADJADJ

2023

Preprint

View full text Add to dashboard Cite

This research investigates the influence of the Gunning Fog Index (GFI) on the production of PlantUML use case diagrams by ChatGPT, within the context of software development projects, particularly focusing on E-commerce for Special Shoes. The study emphasizes the impact of linguistic complexity, as measured by GFI, on the automated code-generation process. It reveals that lower GFI scores, indicative of clearer text, lead to more easily comprehensible code representations, while higher scores correlate with intricate but potentially less accessible code artifacts. This reflects a nuanced balance between detail and clarity in the specifications. A key finding is the significant contribution of integrating linguistic clarity met-rics like GFI into the code generation workflow. This integration is shown to enhance code quality, usability, and facilitate collaboration among stakeholders. Despite the study’s focus on GFI to the exclusion of other readability metrics, it provides valuable insights into the role of linguistic complexity in shaping software artifacts generated by ChatGPT. Recognizing the importance of readability allows developers to more effectively translate natural language specifications into machine-generated code, yielding benefits in diverse project scenarios.

show abstract

“…Usage of requirement management tools is still uncommon, in international railway projects, although some project partners may be familiar with such tools. In this regard, the railway world does not seem to belong to the 17.8% of survey respondents having "strong knowledge" of using requirements management tools, but definitely to the 69% using a "systematic methodology" for collecting requirements [9]. Natural Language Processing can be excluded from the solutions, lacking comprehensive, published, and widely used domain ontologies 6 .…”

Section: Formalizing Data Requirementsmentioning

confidence: 99%

Formalization and Processing of Data Requirements for the Development of Next Generation Railway Traffic Management Systems

Magnien,

Cecchetti,

Ruscelli

et al. 2022

Reliability, Safety, and Security of Railway Systems. Modelling, Analysis, Verification, and Certification

View full text Add to dashboard Cite

Railway Traffic Management Systems (TMSs) handle data from multiple railway subsystems, including Rail Business Services (such as interlocking, RBC, maintenance service, etc.) and external services (such as passenger information systems, weather forecast, etc.). In turn, the data from these subsystems are described in several models or ontologies contributed by various organizations or projects which are in a process of converging or federation. The challenge of the Shift2Rail OPTIMA project, which is implementing a communication platform for virtual testing of new applications for railway TMS, is to allow the exchange of data between different services or users and to support new traffic management applications, enabling access to a large number of disparate data sources. In this paper, the core activities of the OPTIMA project related to the formulation and standardization of a common data model are described. A new Common Data Model is developed based on standardized data structures to enable the seamless exchange of large amounts of data between different and heterogeneous sources and consumers of data, that contributes to the building of next generation of a more effective and efficient railway TMS suitable to offer precise and real-time traffic information to railway operators and other end users.

show abstract

From Requirements Engineering to UML using Natural Language Processing – Survey Study

Cited by 29 publications

References 12 publications

Requirement Formalisation Using Natural Language Processing and Machine Learning: A Systematic Review

Requirement Formalisation Using Natural Language Processing and Machine Learning: A Systematic Review

Gunning Fog Index and Automated UML Generation

Formalization and Processing of Data Requirements for the Development of Next Generation Railway Traffic Management Systems

Contact Info

Product

Resources

About