Open this publication in new window or tab >>2022 (English)In: ICSE '22: Proceedings of the 44th International Conference on Software Engineering, Association for Computing Machinery (ACM) , 2022, p. 1506-1518Conference paper, Published paper (Refereed)
Abstract [en]
Neural machine translation (NMT) architectures have achieved promising results for automatic program repair. Yet, they have the limitation of generating low-quality patches (e.g., not compilable patches). This is because the existing works only optimize a purely syntactic loss function based on characters and tokens without incorporating program-specific information during neural network weight optimization. In this paper, we propose a novel program repair model called RewardRepair. The core novelty of RewardRepair is to improve NMT-based program repair with a loss function based on program compilation and test execution information, rewarding the network to produce patches that compile and that do not overfit. We conduct several experiments to evaluate RewardRepair showing that it is feasible and effective to use compilation and test execution results to optimize the underlying neural repair model. RewardRepair correctly repairs 207 bugs over four benchmarks. we report on repair success for 121 bugs that are fixed for the first time in the literature. Also, RewardRepair produces up to 45.3% of compilable patches, an improvement over the 39% by the state-of-the-art.
Place, publisher, year, edition, pages
Association for Computing Machinery (ACM), 2022
Series
International Conference on Software Engineering, ISSN 0270-5257
National Category
Specific Languages Computer Sciences
Identifiers
urn:nbn:se:kth:diva-316694 (URN)10.1145/3510003.3510222 (DOI)000832185400122 ()2-s2.0-85130298109 (Scopus ID)
Conference
44th ACM/IEEE International Conference on Software Engineering, ICSE 2022, Pittsburgh, 22 May 2022, through 27 May 2022
Funder
Wallenberg AI, Autonomous Systems and Software Program (WASP)
Note
QC 20221109
Part of proceedings: ISBN 978-145039221-1
2022-09-052022-09-052023-02-08Bibliographically approved