Improving bug detection and fixing via code representation learning
Document Type
Conference Proceeding
Publication Date
6-27-2020
Abstract
The software quality and reliability have been proved to be important during the program development. There are many existingstudies trying to help improve it on bug detection and automatedprogram repair processes. However, each of them has its own limitation and the overall performance still have some improvementspace. In this paper, we proposed a deep learning framework toimprove the software quality and reliability on these two detectfix processes. We used advanced code modeling and AI models tohave some improvements on the state-of-the-art approaches. Theevaluation results show that our approach can have a relative improvement up to 206% in terms of F-1 score when comparing withbaselines on bug detection and can have a relative improvementup to 19.8 times on the correct bug-fixing amount when comparing with baselines on automated program repair. These results canprove that our framework can have an outstanding performanceon improving software quality and reliability in bug detection andautomated program repair processes.
Identifier
85094145554 (Scopus)
ISBN
[9781450371223]
Publication Title
Proceedings International Conference on Software Engineering
External Full Text Location
https://doi.org/10.1145/3377812.3382172
ISSN
02705257
First Page
137
Last Page
139
Recommended Citation
Li, Yi, "Improving bug detection and fixing via code representation learning" (2020). Faculty Publications. 5201.
https://digitalcommons.njit.edu/fac_pubs/5201
