An Empirical Study on Software Defect Prediction Using CodeBERT Model

Deep learning-based software defect prediction has been popular these days. Recently, the publishing of the CodeBERT model has made it possible to perform many software engineering tasks. We propose various CodeBERT models targeting software defect prediction, including CodeBERT-NT, CodeBERT-PS, Cod...

Full description

Saved in:
Bibliographic Details
Published inApplied sciences Vol. 11; no. 11; p. 4793
Main Authors Pan, Cong, Lu, Minyan, Xu, Biao
Format Journal Article
LanguageEnglish
Published Basel MDPI AG 01.06.2021
Subjects
Computer programs
Datasets
Deep learning
deep transfer learning
Language
Natural language processing
Neural networks
pre-trained language model
Predictions
Programming languages
Researchers
Semantics
Software
software defect prediction
Software engineering
Software reliability
Syntax
Online AccessGet full text

Cover

More Information
Summary:Deep learning-based software defect prediction has been popular these days. Recently, the publishing of the CodeBERT model has made it possible to perform many software engineering tasks. We propose various CodeBERT models targeting software defect prediction, including CodeBERT-NT, CodeBERT-PS, CodeBERT-PK, and CodeBERT-PT. We perform empirical studies using such models in cross-version and cross-project software defect prediction to investigate if using a neural language model like CodeBERT could improve prediction performance. We also investigate the effects of different prediction patterns in software defect prediction using CodeBERT models. The empirical results are further discussed.
ISSN:2076-3417
2076-3417
DOI:10.3390/app11114793