Paper Info
Title
Applying CodeBERT for Automated Program Repair of Java Simple Bugs
Abstract
Software debugging, and program repair are among the most time-consuming and labor-intensive tasks in software engineering that would benefit a lot from automation. In this paper, we propose a novel automated program repair approach based on CodeBERT, which is a transformer-based neural architecture pre-trained on large corpus of source code. We fine-tune our model on the ManySStuBs4J small and la...
Year
DOI
Venue
2021
10.1109/MSR52588.2021.00063
2021 IEEE/ACM 18th International Conference on Mining Software Repositories (MSR)
Keywords
DocType
ISSN
Training,Java,Automation,Computer bugs,Computer architecture,Maintenance engineering,Data mining
Conference
2160-1852
ISBN
Citations 
PageRank 
978-1-7281-8710-5
4
0.43
References 
Authors
0
2
Name
Order
Citations
PageRank
Ehsan Mashhadi140.43
Hadi Hemmati262227.54