Transforming natural language into code: advancing automated code synthesis for software development

Automated code generation from natural language is a growing challenge in software engineering, enabling the direct translation of requirements into executable code. Machine learning-based automatic code synthesis emerged as a key solution, with transformer-based models playing a pivotal role in enh...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Cluster computing Ročník 28; číslo 15; s. 967
Hlavní autoři: Al shboul, Bashar, Qaqour, Ali, Bani-Salameh, Hani, Almakadmeh, Khaled
Médium: Journal Article
Jazyk:angličtina
Vydáno: New York Springer US 01.12.2025
Springer Nature B.V
Témata:
Algorithms
Artificial intelligence
Automation
Code reuse
Computer Communication Networks
Computer Science
Datasets
Efficiency
Embedded systems
Java
Machine learning
Mathematical functions
Multilingualism
Natural language processing
Operating Systems
Processor Architectures
Productivity
Programming languages
Python
Software development
Software engineering
Source code
Speech recognition
Synthesis
Task complexity
Machine learning in software development
Automated code synthesis
Software engineering automation
Transformer-based models
Program synthesis
Natural language programming
ISSN:1386-7857, 1573-7543
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:Automated code generation from natural language is a growing challenge in software engineering, enabling the direct translation of requirements into executable code. Machine learning-based automatic code synthesis emerged as a key solution, with transformer-based models playing a pivotal role in enhancing this process. This paper addresses the challenges of generating accurate, functional code efficiently. This paper presents a transformer-based T5 model fine-tuned on the multilingual XLCoST dataset for code generation. The model is evaluated using a novel systematic multi-level evaluation framework. The framework evaluates the model’s across three distinct task complexity levels ranging from beginner to advanced. The evaluation results highlight the model’s versatility and robustness. Furthermore, the model achieves a BLEU score of 30.093, demonstrating competitive performance compared to open-source baselines. The model’s code generation abilities accelerates software development by reducing manual coding efforts, thereby improving workflow efficiency and software quality. These results confirm that transformer-based models are effective tools for automating software development, with promising implications for the future.
Bibliografie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:1386-7857
1573-7543
DOI:10.1007/s10586-025-05688-0