Evaluating Representation Learning of Code Changes for Predicting Patch Correctness in Program Repair
作者： Tegawendé F. Bissyandé , Jacques Klein , Anil Koyuncu , Kui Liu , Abdoul Kader Kaboreé
DOI:
关键词: Transformer (machine learning model) 、 Oracle 、 Computation 、 Feature learning 、 Test suite 、 Correctness 、 Computer science 、 Machine learning 、 Heuristics 、 Artificial neural network 、 Artificial intelligence
摘要: A large body of the literature of automated program repair develops approaches where patches are generated to be validated against an oracle (eg, a test suite). Because such an oracle can be imperfect, the generated patches, although validated by the oracle, may actually be incorrect. While the state of the art explore research directions that require dynamic information or that rely on manually-crafted heuristics, we study the benefit of learning code representations in order to learn deep features that may encode the …
arxiv.org
harvard.edu
acm.org参考文章(65)
Westley Weimer, ThanhVu Nguyen, Claire Le Goues, Stephanie Forrest, Automatically finding patches using genetic programming international conference on software engineering. pp. 364- 374 ,(2009) , 10.1109/ICSE.2009.5070536
Tomas Mikolov, Quoc Le, Distributed Representations of Sentences and Documents international conference on machine learning. ,vol. 4, pp. 1188- 1196 ,(2014)
Miltiadis Allamanis, Charles Sutton, Christian Bird, Earl T. Barr, Learning natural coding conventions foundations of software engineering. pp. 281- 293 ,(2014) , 10.1145/2635868.2635883
Premkumar Devanbu, Zhendong Su, Abram Hindle, Earl T. Barr, Mark Gabel, On the naturalness of software international conference on software engineering. pp. 837- 847 ,(2012) , 10.5555/2337223.2337322
Claire Le Goues, ThanhVu Nguyen, Stephanie Forrest, Westley Weimer, GenProg: A Generic Method for Automatic Software Repair IEEE Transactions on Software Engineering. ,vol. 38, pp. 54- 72 ,(2012) , 10.1109/TSE.2011.104
Zichao Qi, Fan Long, Sara Achour, Martin Rinard, An analysis of patch plausibility and correctness for generate-and-validate patch generation systems international symposium on software testing and analysis. pp. 24- 36 ,(2015) , 10.1145/2771783.2771791
René Just, Darioush Jalali, Michael D. Ernst, Defects4J: a database of existing faults to enable controlled testing studies for Java programs Proceedings of the 2014 International Symposium on Software Testing and Analysis - ISSTA 2014. pp. 437- 440 ,(2014) , 10.1145/2610384.2628055
Martin Monperrus, Matias Martinez, Mining software repair models for reasoning on the search space of automated program fixing Empirical Software Engineering. ,vol. 20, pp. 176- 205 ,(2015) , 10.1007/S10664-013-9282-8
Fan Long, Martin Rinard, Automatic patch generation by learning correct code symposium on principles of programming languages. ,vol. 51, pp. 298- 312 ,(2016) , 10.1145/2837614.2837617
Song Wang, Taiyue Liu, Lin Tan, Automatically learning semantic features for defect prediction international conference on software engineering. pp. 297- 308 ,(2016) , 10.1145/2884781.2884804