From Prose to Prototype: Synthesising Executable UML Models from Natural Language

Guus J. Ramackers; Pepijn P. Griffioen; Martijn B.J. Schouten; Michel R.V. Chaudron

doi:10.1109/MODELS-C53483.2021.00061

From Prose to Prototype: Synthesising Executable UML Models from Natural Language

Guus J. Ramackers, Pepijn P. Griffioen, Martijn B.J. Schouten, Michel R.V. Chaudron

Engineering of Software-Intensive Systems

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

4 Citations (Scopus)

Abstract

This paper presents a vision for a development tool that provides automated support for synthesising UML models from requirements text expressed in natural language. This approach aims to simplify the process of analysis - i.e. moving from written (and spoken) descriptions of the functionality of a system and a domain to an executable specification of that system. The contribution focuses on the AI techniques used to transform natural language into structural and dynamic UML models. Moreover, we envision a 'human-in-the-loop' approach where an interactive conversational component is used based on machine learning of the system under construction and corpora of external natural language texts and UML models. To illustrate the approach, we present a tool prototype. As a scoping, this approach targets data-intensive systems rather than control-intensive (embedded) systems.

Original language	English
Title of host publication	Companion Proceedings - 24th International Conference on Model-Driven Engineering Languages and Systems, MODELS-C 2021
Publisher	Institute of Electrical and Electronics Engineers
Pages	380-389
Number of pages	10
ISBN (Electronic)	9781665424844
DOIs	https://doi.org/10.1109/MODELS-C53483.2021.00061
Publication status	Published - 2021
Event	24th International Conference on Model-Driven Engineering Languages and Systems, MODELS-C 2021 - Virtual, Online, Japan Duration: 10 Oct 2021 → 15 Oct 2021

Conference

Conference	24th International Conference on Model-Driven Engineering Languages and Systems, MODELS-C 2021
Country/Territory	Japan
City	Virtual, Online
Period	10/10/21 → 15/10/21

Bibliographical note

Publisher Copyright:
© 2021 IEEE.

Keywords

executable specification
MDA
model driven engineering
natural language processing
requirement text
transformer architecture
UML

Access to Document

10.1109/MODELS-C53483.2021.00061

Cite this

Ramackers, G. J., Griffioen, P. P., Schouten, M. B. J., & Chaudron, M. R. V. (2021). From Prose to Prototype: Synthesising Executable UML Models from Natural Language. In Companion Proceedings - 24th International Conference on Model-Driven Engineering Languages and Systems, MODELS-C 2021 (pp. 380-389). Institute of Electrical and Electronics Engineers. https://doi.org/10.1109/MODELS-C53483.2021.00061

@inproceedings{fab75f7bda714424b4904c22d34619b1,

title = "From Prose to Prototype: Synthesising Executable UML Models from Natural Language",

abstract = "This paper presents a vision for a development tool that provides automated support for synthesising UML models from requirements text expressed in natural language. This approach aims to simplify the process of analysis - i.e. moving from written (and spoken) descriptions of the functionality of a system and a domain to an executable specification of that system. The contribution focuses on the AI techniques used to transform natural language into structural and dynamic UML models. Moreover, we envision a 'human-in-the-loop' approach where an interactive conversational component is used based on machine learning of the system under construction and corpora of external natural language texts and UML models. To illustrate the approach, we present a tool prototype. As a scoping, this approach targets data-intensive systems rather than control-intensive (embedded) systems.",

keywords = "executable specification, MDA, model driven engineering, natural language processing, requirement text, transformer architecture, UML",

author = "Ramackers, {Guus J.} and Griffioen, {Pepijn P.} and Schouten, {Martijn B.J.} and Chaudron, {Michel R.V.}",

note = "Publisher Copyright: {\textcopyright} 2021 IEEE.; 24th International Conference on Model-Driven Engineering Languages and Systems, MODELS-C 2021 ; Conference date: 10-10-2021 Through 15-10-2021",

year = "2021",

doi = "10.1109/MODELS-C53483.2021.00061",

language = "English",

pages = "380--389",

booktitle = "Companion Proceedings - 24th International Conference on Model-Driven Engineering Languages and Systems, MODELS-C 2021",

publisher = "Institute of Electrical and Electronics Engineers",

address = "United States",

}

Ramackers, GJ, Griffioen, PP, Schouten, MBJ & Chaudron, MRV 2021, From Prose to Prototype: Synthesising Executable UML Models from Natural Language. in Companion Proceedings - 24th International Conference on Model-Driven Engineering Languages and Systems, MODELS-C 2021. Institute of Electrical and Electronics Engineers, pp. 380-389, 24th International Conference on Model-Driven Engineering Languages and Systems, MODELS-C 2021, Virtual, Online, Japan, 10/10/21. https://doi.org/10.1109/MODELS-C53483.2021.00061

From Prose to Prototype: Synthesising Executable UML Models from Natural Language. / Ramackers, Guus J.; Griffioen, Pepijn P.; Schouten, Martijn B.J. et al.
Companion Proceedings - 24th International Conference on Model-Driven Engineering Languages and Systems, MODELS-C 2021. Institute of Electrical and Electronics Engineers, 2021. p. 380-389.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

TY - GEN

T1 - From Prose to Prototype

T2 - 24th International Conference on Model-Driven Engineering Languages and Systems, MODELS-C 2021

AU - Ramackers, Guus J.

AU - Griffioen, Pepijn P.

AU - Schouten, Martijn B.J.

AU - Chaudron, Michel R.V.

PY - 2021

Y1 - 2021

N2 - This paper presents a vision for a development tool that provides automated support for synthesising UML models from requirements text expressed in natural language. This approach aims to simplify the process of analysis - i.e. moving from written (and spoken) descriptions of the functionality of a system and a domain to an executable specification of that system. The contribution focuses on the AI techniques used to transform natural language into structural and dynamic UML models. Moreover, we envision a 'human-in-the-loop' approach where an interactive conversational component is used based on machine learning of the system under construction and corpora of external natural language texts and UML models. To illustrate the approach, we present a tool prototype. As a scoping, this approach targets data-intensive systems rather than control-intensive (embedded) systems.

AB - This paper presents a vision for a development tool that provides automated support for synthesising UML models from requirements text expressed in natural language. This approach aims to simplify the process of analysis - i.e. moving from written (and spoken) descriptions of the functionality of a system and a domain to an executable specification of that system. The contribution focuses on the AI techniques used to transform natural language into structural and dynamic UML models. Moreover, we envision a 'human-in-the-loop' approach where an interactive conversational component is used based on machine learning of the system under construction and corpora of external natural language texts and UML models. To illustrate the approach, we present a tool prototype. As a scoping, this approach targets data-intensive systems rather than control-intensive (embedded) systems.

KW - executable specification

KW - MDA

KW - model driven engineering

KW - natural language processing

KW - requirement text

KW - transformer architecture

KW - UML

UR - http://www.scopus.com/inward/record.url?scp=85124014631&partnerID=8YFLogxK

U2 - 10.1109/MODELS-C53483.2021.00061

DO - 10.1109/MODELS-C53483.2021.00061

M3 - Conference contribution

AN - SCOPUS:85124014631

SP - 380

EP - 389

BT - Companion Proceedings - 24th International Conference on Model-Driven Engineering Languages and Systems, MODELS-C 2021

PB - Institute of Electrical and Electronics Engineers

Y2 - 10 October 2021 through 15 October 2021

ER -

From Prose to Prototype: Synthesising Executable UML Models from Natural Language

Abstract

Conference

Bibliographical note

Keywords

Access to Document

Other files and links

Fingerprint

Cite this