Zobrazeno 1 - 10
of 278
pro vyhledávání: '"BAVOTA, GABRIELE"'
Autor:
Tufano, Rosalia, Martin-Lopez, Alberto, Tayeb, Ahmad, Dabić, Ozren, Haiduc, Sonia, Bavota, Gabriele
Several techniques have been proposed to automate code review. Early support consisted in recommending the most suited reviewer for a given change or in prioritizing the review tasks. With the advent of deep learning in software engineering, the leve
Externí odkaz:
http://arxiv.org/abs/2411.11401
Large-scale code datasets have acquired an increasingly central role in software engineering (SE) research. This is the result of (i) the success of the mining software repositories (MSR) community, that pushed the standards of empirical studies in S
Externí odkaz:
http://arxiv.org/abs/2409.18658
Autor:
Pepe, Federica, Zampetti, Fiorella, Mastropaolo, Antonio, Bavota, Gabriele, Di Penta, Massimiliano
Publikováno v:
Proceedings of the 40th IEEE International Conference on Software Maintenance and Evolution (ICSME 2024)
The development of Machine Learning (ML)- and, more recently, of Deep Learning (DL)-intensive systems requires suitable choices, e.g., in terms of technology, algorithms, and hyper-parameters. Such choices depend on developers' experience, as well as
Externí odkaz:
http://arxiv.org/abs/2409.11826
Generative deep learning (DL) models have been successfully adopted for vulnerability patching. However, such models require the availability of a large dataset of patches to learn from. To overcome this issue, researchers have proposed to start from
Externí odkaz:
http://arxiv.org/abs/2404.17896
Code completion is a key feature of Integrated Development Environments (IDEs), aimed at predicting the next tokens a developer is likely to write, helping them write code faster and with less effort. Modern code completion approaches are often power
Externí odkaz:
http://arxiv.org/abs/2403.15149
Autor:
Tufano, Rosalia, Mastropaolo, Antonio, Pepe, Federica, Dabić, Ozren, Di Penta, Massimiliano, Bavota, Gabriele
Large Language Models (LLMs) have gained significant attention in the software engineering community. Nowadays developers have the possibility to exploit these models through industrial-grade tools providing a handy interface toward LLMs, such as Ope
Externí odkaz:
http://arxiv.org/abs/2402.16480
Autor:
Mastropaolo, Antonio, Ciniselli, Matteo, Pascarella, Luca, Tufano, Rosalia, Aghajani, Emad, Bavota, Gabriele
When comprehending code, a helping hand may come from the natural language comments documenting it that, unfortunately, are not always there. To support developers in such a scenario, several techniques have been presented to automatically generate n
Externí odkaz:
http://arxiv.org/abs/2402.00519
The automation of code review has been tackled by several researchers with the goal of reducing its cost. The adoption of deep learning in software engineering pushed the automation to new boundaries, with techniques imitating developers in generativ
Externí odkaz:
http://arxiv.org/abs/2401.05136
Several code summarization techniques have been proposed in the literature to automatically document a code snippet or a function. Ideally, software developers should be involved in assessing the quality of the generated summaries. However, in most c
Externí odkaz:
http://arxiv.org/abs/2312.15475
Logging assists in monitoring events that transpire during the execution of software. Previous research has highlighted the challenges confronted by developers when it comes to logging, including dilemmas such as where to log, what data to record, an
Externí odkaz:
http://arxiv.org/abs/2311.04587