EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC-ND 4.0

A systematic mapping study of source code representation for deep learning in software engineering

Hazem Peter Samoaa, Firas Bayram, Pasquale Salza, Philipp Leitner

IET Software · 2022-08 · 16 (4) · 351-385

DOI: 10.1049/sfw2.12064 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IET Software, online erschienen am 07.06.2022. Verfasst von Hazem Peter Samoaa und 3 weiteren Autor:innen. Die Arbeit wurde bisher 33-mal zitiert (Crossref) und nennt 144 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The usage of deep learning (DL) approaches for software engineering has attracted much attention, particularly in source code modelling and analysis. However, in order to use DL, source code needs to be formatted to fit the expected input form of DL models. This problem is known as source code representation. Source code can be represented via different approaches, most importantly, the tree‐based, token‐based, and graph‐based approaches. We use a systematic mapping study to investigate i detail the representation approaches adopted in 103 studies that use DL in the context of software engineering. Thus, studies are collected from 2014 to 2021 from 14 different journals and 27 conferences. We show that each way of representing source code can provide a different, yet orthogonal view of the same source code. Thus, different software engineering tasks might require different (combinations of) code representation approaches, depending on the nature and complexity of the task. Particularly, we show that it is crucial to define whether the DL approach requires lexical, syntactical, or semantic code information. Our analysis shows that a wide range of different representations and combinations of representations (hybrid representations) are used to solve a wide range of common software engineering problems. However, we also observe that current research does not generally attempt to transfer existing representations or models to other studies even though there are other contexts in which these representations and models may also be useful. We believe that there is potential for more reuse and the application of transfer learning when applying DL to software engineering tasks.

Zitieren

APA

Samoaa, H. P., Bayram, F., Salza, P., & Leitner, P. (2022). A systematic mapping study of source code representation for deep learning in software engineering. IET Software, 16(4), 351-385. https://doi.org/10.1049/sfw2.12064

Vancouver

Samoaa HP, Bayram F, Salza P, Leitner P. A systematic mapping study of source code representation for deep learning in software engineering. IET Software. 2022;16(4):351-385. doi:10.1049/sfw2.12064

BibTeX
@article{Samoaa2022,
  author = {Samoaa, Hazem Peter and Bayram, Firas and Salza, Pasquale and Leitner, Philipp},
  title = {A systematic mapping study of source code representation for deep learning in software engineering},
  journal = {IET Software},
  year = {2022},
  volume = {16},
  number = {4},
  pages = {351--385},
  doi = {10.1049/sfw2.12064}
}
Kostenlos starten →