RTFM: Towards Understanding Source Code using Natural Language Processing

Galanis, Maximilian; Dietrich, Vincent; Kast, Bernd; Fiegert, Michael

doi:10.5220/0009826604300437

Cited by 1 publication

(2 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, source code is also designed as a means of communication between humans. Program source code requires to be designed in a manner that can be understood and maintained between developers 58 . Therefore, it is reasonable to interpret source code as a means of communication amenable to the same sorts of statistical language models in NLP.…”

Section: Discussionmentioning

confidence: 99%

“…Program source code requires to be designed in a manner that can be understood and maintained between developers. 58 Therefore, it is reasonable to interpret source code as a means of communication amenable to the same sorts of statistical language models in NLP. A community of individuals governs the evolution of programming languages.…”

Section: Source Code and Natural Languagementioning

confidence: 99%

See 1 more Smart Citation

An empirical evaluation of deep learning‐based source code vulnerability detection: Representation versus models

Semasaba

Zheng

et al. 2022

J Software Evolu Process

View full text Add to dashboard Cite

Vulnerabilities in the source code of the software are critical issues in the realm of software engineering. Coping with vulnerabilities in software source code is becoming more challenging due to several aspects such as complexity and volume. Deep learning has gained popularity throughout the years as a means of addressing such issues. This paper proposes an evaluation of vulnerability detection performance on source code representations and evaluates how machine learning (ML) strategies can improve them. The structure of our experiment consists of three deep neural networks (DNNs) in conjunction with five different source code representations: abstract syntax trees (ASTs), code gadgets (CGs), semantics‐based vulnerability candidates (SeVCs), lexed code representations (LCRs), and composite code representations (CCRs). Experimental results show that employing different ML strategies in conjunction with the base model structure influences the performance results to a varying degree. However, ML‐based techniques suffer from poor performance on class imbalance handling and dimensionality reduction when used in conjunction with source code representations.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Source Code and Natural Languagementioning

confidence: 99%