DeepOCL: A deep neural network for Object Constraint Language generation from unrestricted nature language

Guardat en:
Dades bibliogràfiques
Publicat a:CAAI Transactions on Intelligence Technology vol. 9, no. 1 (Feb 1, 2024), p. 250
Autor principal: Yang, Yilong
Altres autors: Liu, Yibo, Bao, Tianshu, Wang, Weiru, Niu, Nan, Yin, Yongfeng
Publicat:
John Wiley & Sons, Inc.
Matèries:
Accés en línia:Citation/Abstract
Full Text
Full Text - PDF
Etiquetes: Afegir etiqueta
Sense etiquetes, Sigues el primer a etiquetar aquest registre!

MARC

LEADER 00000nab a2200000uu 4500
001 3192195979
003 UK-CbPIL
022 |a 2468-2322 
024 7 |a 10.1049/cit2.12207  |2 doi 
035 |a 3192195979 
045 0 |b d20240201 
100 1 |a Yang, Yilong  |u School of Software, Beihang University, Beijing, China 
245 1 |a DeepOCL: A deep neural network for Object Constraint Language generation from unrestricted nature language 
260 |b John Wiley & Sons, Inc.  |c Feb 1, 2024 
513 |a Journal Article 
520 3 |a Object Constraint Language (OCL) is one kind of lightweight formal specification, which is widely used for software verification and validation in NASA and Object Management Group projects. Although OCL provides a simple expressive syntax, it is hard for the developers to write correctly due to lacking knowledge of the mathematical foundations of the first‐order logic, which is approximately half accurate at the first stage of development. A deep neural network named DeepOCL is proposed, which takes the unrestricted natural language as inputs and automatically outputs the best‐scored OCL candidates without requiring a domain conceptual model that is compulsively required in existing rule‐based generation approaches. To demonstrate the validity of our proposed approach, ablation experiments were conducted on a new sentence‐aligned dataset named OCLPairs. The experiments show that the proposed DeepOCL can achieve state of the art for OCL statement generation, scored 74.30 on BLEU, and greatly outperformed experienced developers by 35.19%. The proposed approach is the first deep learning approach to generate the OCL expression from the natural language. It can be further developed as a CASE tool for the software industry. 
653 |a Language 
653 |a Deep learning 
653 |a Datasets 
653 |a Syntax 
653 |a Artificial neural networks 
653 |a Bar codes 
653 |a Ablation 
653 |a Project management 
653 |a Formal specifications 
653 |a Knowledge management 
653 |a Program verification (computers) 
653 |a Machine learning 
653 |a Queries 
653 |a Constraints 
653 |a Software engineering 
653 |a Software 
653 |a Semantics 
653 |a Natural language 
700 1 |a Liu, Yibo  |u School of Software, Beihang University, Beijing, China 
700 1 |a Bao, Tianshu  |u College of Computer Science and Technology, Guizhou University, Guiyang, Guizhou, China 
700 1 |a Wang, Weiru  |u Faculty of Information Technology, Beijing University of Technology, Beijing, China 
700 1 |a Niu, Nan  |u Department of Electrical Engineering and Computer Sciences, University of Cincinnati, Cincinnati, Ohio, USA 
700 1 |a Yin, Yongfeng  |u School of Software, Beihang University, Beijing, China 
773 0 |t CAAI Transactions on Intelligence Technology  |g vol. 9, no. 1 (Feb 1, 2024), p. 250 
786 0 |d ProQuest  |t Computer Science Database 
856 4 1 |3 Citation/Abstract  |u https://www.proquest.com/docview/3192195979/abstract/embedded/6A8EOT78XXH2IG52?source=fedsrch 
856 4 0 |3 Full Text  |u https://www.proquest.com/docview/3192195979/fulltext/embedded/6A8EOT78XXH2IG52?source=fedsrch 
856 4 0 |3 Full Text - PDF  |u https://www.proquest.com/docview/3192195979/fulltextPDF/embedded/6A8EOT78XXH2IG52?source=fedsrch