2021

CURE: Code-Aware Neural Machine Translation for Automatic Program Repair

Jiang, Nan, Lutellier, Thibaud, Tan, Lin

Understand

Automatic program repair (APR) is crucial to improve software reliability.

Recently, neural machine translation (NMT) techniques have been used to fix software bugs automatically.
While promising, these approaches have two major limitations.
Their search space often does not contain the correct fix, and their search strategy ignores software knowledge such as strict code syntax.

Built on

C. Le Goues, T. Nguyen, S. Forrest, and W. Weimer, “GenProg: A Generic Method for Automatic Software Repair,” TSE , vol. 38, no. 1, pp. 54–72, 2012
2012
Earlier work this paper cites.
G. Gousios and D. Spinellis, “GHTorrent: GitHub’s data from a firehose,” in MSR . IEEE, 2012, pp. 12–21
2012
Earlier work this paper cites.
D. Kim, J. Nam, J. Song, and S. Kim, “Automatic Patch Generation Learned from Human-Written Patches,” in ICSE . IEEE, 2013, pp. 802–811
2013
Earlier work this paper cites.
Y. Qi, X. Mao, Y. Lei, Z. Dai, and C. Wang, “Does Genetic Programming Work Well on Automated Program Repair?” in ICCIS . IEEE, 2013, pp. 1875–1878
2013
Earlier work this paper cites.
F. S. Ocariza, Jr, K. Pattabiraman, and A. Mesbah, “Vejovis: Suggesting Fixes for JavaScript Faults,” in ICSE . ACM, 2014, pp. 837–847
2014
Earlier work this paper cites.
I. Sutskever, O. Vinyals, and Q. V. Le, “Sequence to Sequence Learning with Neural Networks,” in NeurIPS . MIT Press, 2014, pp. 3104–3112
2014
Earlier work this paper cites.
R. Just, D. Jalali, and M. D. Ernst, “Defects4J: A Database of Existing Faults to Enable Controlled Testing Studies for Java Programs,” in ISSTA , 2014, pp. 437–440
2014
Earlier work this paper cites.
F. Long and M. Rinard, “Staged Program Repair with Condition Synthesis,” in ESEC/FSE . ACM, 2015, pp. 166–178
2015
Earlier work this paper cites.
M. Tan, L. Tan, S. Dara, and C. Mayeux, “Online Defect Prediction for Imbalanced Data,” in ICSE-SEIP , 2015, pp. 99–108
2015
Earlier work this paper cites.
D. P. Kingma and J. Ba, “Adam: A Method for Stochastic Optimization,” in ICLR , 2015
2015
Earlier work this paper cites.
Z. Qi, F. Long, S. Achour, and M. Rinard, “An Analysis of Patch Plausibility and Correctness for Generate-and-Validate Patch Generation Systems,” in ISSTA . ACM, 2015, pp. 24–36
2015
Earlier work this paper cites.
M. White, C. Vendome, M. Linares-Vásquez, and D. Poshyvanyk, “Toward Deep Learning Software Repositories,” in MSR . IEEE, 2015, pp. 334–345
2015
Earlier work this paper cites.
M. Martinez and M. Monperrus, “ASTOR: A Program Repair Library for Java (Demo),” in ISSTA . ACM, 2016, pp. 441–444
2016
Earlier work this paper cites.
X. B. D. Le, D. Lo, and C. Le Goues, “History Driven Program Repair,” in SANER , vol. 1. IEEE, 2016, pp. 213–224
2016
Earlier work this paper cites.
S. Wang, T. Liu, and L. Tan, “Automatically Learning Semantic Features for Defect Prediction,” in ICSE . IEEE, 2016, pp. 297–308
2016
Earlier work this paper cites.
F. Long and M. Rinard, “An Analysis of the Search Spaces for Generate and Validate Patch Generation Systems,” in ICSE . IEEE, 2016, p. 702–713
2016
Earlier work this paper cites.
S. Rico, H. Barry, and B. Alexandra, “Neural Machine Translation of Rare Words with Subword Units,” Annual Meeting of the ACL , 2016
2016
Earlier work this paper cites.
T. Durieux and M. Monperrus, “DynaMoth: Dynamic Code Synthesis for Automatic Program Repair,” in AST , 2016, pp. 85–91
2016
Earlier work this paper cites.
M. White, M. Tufano, C. Vendome, and D. Poshyvanyk, “Deep Learning Code Fragments for Code Clone Detection,” in ASE . ACM, 2016, pp. 87–98
2016
Earlier work this paper cites.
W. Ling, E. Grefenstette, K. M. Hermann, T. Kočiskỳ, A. Senior, F. Wang, and P. Blunsom, “Latent Predictor Networks for Code Generation,” Annual Meeting of the ACL , 2016
2016
Earlier work this paper cites.
R. K. Saha, Y. Lyu, H. Yoshida, and M. R. Prasad, “ELIXIR: Effective Object Oriented Program Repair,” in ASE . IEEE, 2017, pp. 648–659
2017
Earlier work this paper cites.
J. Xuan, M. Martinez, F. Demarco, M. Clement, S. L. Marcote, T. Durieux, D. Le Berre, and M. Monperrus, “Nopol: Automatic Repair of Conditional Statement Bugs in Java Programs,” TSE , vol. 43, no. 1, pp. 34–55, 2017
2017
Earlier work this paper cites.
F. Long, P. Amidon, and M. Rinard, “Automatic Inference of Code Transforms for Patch Generation,” in ESEC/FSE . ACM, 2017, p. 727–739
2017
Earlier work this paper cites.
Q. Xin and S. P. Reiss, “Leveraging Syntax-Related Code for Automated Program Repair,” in ASE . IEEE, 2017, p. 660–670
2017
Earlier work this paper cites.
Y. Xiong, J. Wang, R. Yan, J. Zhang, S. Han, G. Huang, and L. Zhang, “Precise Condition Synthesis for Program Repair,” in ICSE . IEEE, 2017, pp. 416–426
2017
Earlier work this paper cites.
L. Chen, Y. Pei, and C. A. Furia, “Contract-Based Program Repair without the Contracts,” in ASE . IEEE, 2017, pp. 637–647
2017
Earlier work this paper cites.
E. A. Santos, J. C. Campbell, A. Hindle, and J. N. Amaral, “Finding and Correcting Syntax Errors Using Recurrent Neural Networks,” PeerJ PrePrints , vol. 5, p. e3123v1, 2017
2017
Earlier work this paper cites.
R. Gupta, S. Pal, A. Kanade, and S. Shevade, “Deepfix: Fixing Common C Language Errors by Deep Learning,” in AAAI , 2017, pp. 1345–1351
2017
Earlier work this paper cites.
J. Gehring, M. Auli, D. Grangier, D. Yarats, and Y. N. Dauphin, “Convolutional Sequence to Sequence Learning,” in ICML . JMLR.org, 2017, pp. 1243––1252
2017
Earlier work this paper cites.
A. Vaswani, N. Shazeer, N. Parmar, J. Uszkoreit, L. Jones, A. N. Gomez, Ł. Kaiser, and I. Polosukhin, “Attention Is All You Need,” in NeurIPS , 2017, pp. 5998–6008
2017
Earlier work this paper cites.

Similar

J. Yang, A. Zhikhartsev, Y. Liu, and L. Tan, “Better Test Cases for Better Automated Program Repair,” in FSE , ser. ESEC/FSE 2017. ACM, 2017, p. 831–841. [Online]. Available: https://doi.org/10.1145/3106237.3106274
2017
Cited alongside, same era.
D. Lin, J. Koppel, A. Chen, and A. Solar-Lezama, “QuixBugs: A Multi-Lingual Program Repair Benchmark Set Based on the Quixey Challenge,” in SPLASH , 2017, p. 55–56
2017
Cited alongside, same era.
L. Li, H. Feng, W. Zhuang, N. Meng, and B. Ryder, “CCLearner: A Deep Learning-Based Clone Detection Approach,” in ICSME . IEEE, 2017, pp. 249–260
2017
Cited alongside, same era.
J. Li, P. He, J. Zhu, and M. R. Lyu, “Software Defect Prediction via Convolutional Neural Network,” in QRS . IEEE, 2017
2017
Cited alongside, same era.
J. Wang and C. Zhang, “Software reliability prediction using a deep learning model based on the RNN encoder–decoder,” RESS , 2017
2017
Cited alongside, same era.
V. J. Hellendoorn and P. Devanbu, “Are Deep Neural Networks the Best Choice for Modeling Source Code?” in ESEC/FSE . ACM, 2017
2017
Cited alongside, same era.
J. Jiang, Y. Xiong, H. Zhang, Q. Gao, and X. Chen, “Shaping Program Repair Space with Existing Patches and Similar Code,” in ISSTA . ACM, 2018, pp. 298–309
2018
Cited alongside, same era.
J. Hua, M. Zhang, K. Wang, and S. Khurshid, “SketchFix: A Tool for Automated Program Repair Approach Using Lazy Candidate Generation,” in ESEC/FSE . ACM, 2018, pp. 888–891
2018
Cited alongside, same era.
M. Wen, J. Chen, R. Wu, D. Hao, and S.-C. Cheung, “Context-Aware Patch Generation for Better Automated Program Repair,” in ICSE . ACM, 2018
2018
Cited alongside, same era.
X. Liu and H. Zhong, “Mining stackoverflow for program repair,” in SANER . IEEE, 2018, pp. 118–129
2018
Cited alongside, same era.
M. Tufano, C. Watson, G. Bavota, M. Di Penta, M. White, and D. Poshyvanyk, “An Empirical Investigation into Learning Bug-Fixing Patches in the Wild via Neural Machine Translation,” in ASE . ACM, 2018, pp. 832–837
2018
Cited alongside, same era.
I. Skorokhodov, A. Rykachevskiy, D. Emelyanenko, S. Slotin, and A. Ponkratov, “Semi-Supervised Neural Machine Translation with Language Models,” in LoResMT . AMTA, 2018, pp. 37–44
2018
Cited alongside, same era.

Then

K. Liu, A. Koyuncu, T. F. Bissyandé, D. Kim, J. Klein, and Y. Le Traon, “You Cannot Fix What You Cannot Find! An Investigation of Fault Localization Bias in Benchmarking Automated Program Repair Systems,” in ICST . IEEE, 2019, pp. 102–113
2019
Later among the works it cites.
K. Liu, A. Koyuncu, D. Kim, and T. F. Bissyandé, “AVATAR: Fixing Semantic Bugs with Fix Patterns of Static Analysis Violations,” in SANER . IEEE, 2019, pp. 1–12
2019
Later among the works it cites.
F. Madeiral, S. Urli, M. Maia, and M. Monperrus, “Bears: An Extensible Java Bug Benchmark for Automatic Program Repair Studies,” in SANER . IEEE, 2019, pp. 468–478
2019
Later among the works it cites.
E. Dinella, H. Dai, Z. Li, M. Naik, L. Song, and K. Wang, “Hoppity: Learning Graph Transformations to Detect and Fix Bugs in Programs,” in ICLR , 2019
2019
Later among the works it cites.
M. Asad, K. K. Ganguly, and K. Sakib, “Impact Analysis of Syntactic and Semantic Similarities on Patch Prioritization in Automated Program Repair,” in ICSME . IEEE, 2019, pp. 328–332
2019
Later among the works it cites.
A. Ghanbari, S. Benton, and L. Zhang, “Practical Program Repair via Bytecode Mutation,” in ISSTA , 2019
2019
Later among the works it cites.
U. Alon, M. Zilberstein, O. Levy, and E. Yahav, “Code2vec: Learning Distributed Representations of Code,” ACM on Programming Languages , vol. 3, no. POPL, pp. 1–29, 2019
2019
Later among the works it cites.
U. Alon, S. Brody, O. Levy, and E. Yahav, “code2seq: Generating Sequences from Structured Representations of Code,” in ICLR , 2019
2019
Later among the works it cites.
H. Hu, Q. Chen, and Z. Liu, “Code Generation from Supervised Code Embeddings,” in NeurIPS . Springer, 2019, pp. 388–396
2019
Later among the works it cites.
H. J. Kang, T. F. Bissyandé, and D. Lo, “Assessing the Generalizability of code2vec Token Embeddings,” in ASE . IEEE, 2019, pp. 1–12
2019
Later among the works it cites.
L. Jiang, H. Liu, and H. Jiang, “Machine Learning Based Recommendation of Method Names: How Far are We,” in ASE . IEEE, 2019, pp. 602–614
2019
Later among the works it cites.
Y. Li, S. Wang, and T. N. Nguyen, “DLFix: Context-Based Code Transformation Learning for Automated Program Repair,” in ICSE . ACM, 2020, p. 602–614
2020
Later among the works it cites.
T. Lutellier, H. V. Pham, L. Pang, Y. Li, M. Wei, and L. Tan, “CoCoNuT: Combining Context-Aware Neural Translation Models Using Ensemble for Program Repair,” in ISSTA . ACM, 2020, p. 101–114
2020
Later among the works it cites.
Y. Ding, B. Ray, P. Devanbu, and V. J. Hellendoorn, “Patching as Translation: the Data and the Metaphor,” in ASE , 2020
2020
Later among the works it cites.
F. Stahlberg, “Neural Machine Translation: A Review,” JAIR , 2020
2020
Later among the works it cites.
T. Wolf, L. Debut, V. Sanh, J. Chaumond, C. Delangue, A. Moi, P. Cistac, T. Rault, R. Louf, M. Funtowicz, and J. Brew, “HuggingFace’s Transformers: State-of-the-art Natural Language Processing,” in EMNLP , 2020
2020
Later among the works it cites.
A. Koyuncu, K. Liu, T. F. Bissyandé, D. Kim, J. Klein, M. Monperrus, and Y. Le Traon, “FixMiner: Mining relevant fix patterns for automated program repair,” EMSE , pp. 1–45, 2020
2020
Later among the works it cites.
K. Liu, S. Wang, A. Koyuncu, K. Kim, T. F. D. A. Bissyande, D. Kim, P. Wu, J. Klein, X. Mao, and Y. Le Traon, “On the Efficiency of Test Suite based Program Repair: A Systematic Assessment of 16 Automated Repair Systems for Java Programs,” in ICSE , 2020
2020
Later among the works it cites.
H. Tian, K. Liu, A. K. Kaboreé, A. Koyuncu, L. Li, J. Klein, and T. F. Bissyandé, “Evaluating Representation Learning of Code Changes for Predicting Patch Correctness in Program Repair,” in ASE , 2020
2020
Later among the works it cites.
G. Sakkas, M. Endres, B. Cosman, W. Weimer, and R. Jhala, “Type Error Feedback via Analytic Program Repair,” in PLDI , 2020, pp. 16–30
2020
Later among the works it cites.
G. Kavi, E. C. Peter, C. Xinyun, and S. Dawn, “Synthesize, Execute and Debug: Learning to Repair for Neural Program Synthesis,” in NeurIPS , H. Larochelle, M. Ranzato, R. Hadsell, M. Balcan, and H. Lin, Eds., 2020
2020
Later among the works it cites.
L. Fang, L. Ge, Z. Yunfei, and J. Zhi, “Multi-task Learning based Pre-trained Language Model for Code Completion,” in ASE , 2020
2020
Later among the works it cites.
S. Chakraborty, Y. Ding, M. Allamanis, and B. Ray, “CODIT: Code Editing with Tree-Based Neural Models,” TSE , 2020
2020
Later among the works it cites.
W. Wang, Y. Zhang, Y. Sui, Y. Wan, Z. Zhao, J. Wu, P. Yu, and G. Xu, “Reinforcement-Learning-Guided Source Code Summarization via Hierarchical Attention,” TSE , 2020
2020
Later among the works it cites.
T. Hoang, H. J. Kang, D. Lo, and J. Lawall, “CC2Vec: Distributed Representations of Code Changes,” in ICSE . ACM, 2020, p. 518–529
2020
Later among the works it cites.
K. Wang and Z. Su, “Blended, Precise Semantic Program Embeddings,” in PLDI . New York, NY, USA: ACM, 2020, p. 121–134
2020
Later among the works it cites.
W. Wang, Gao and Wang, “Learning Semantic Program Embeddings with Graph Interval Neural Network,” in OOPSLA . ACM, 2020
2020
Later among the works it cites.
J. Keim, A. Kaplan, A. Koziolek, and M. Mirakhorli, “Does BERT Understand Code? – An Exploratory Study on the Detection of Architectural Tactics in Code,” in Software Architecture . Springer, 2020
2020
Later among the works it cites.
M. Allamanis, H. Peng, and C. Sutton, “A Convolutional Attention Network for Extreme Summarization of Source Code,” in ICML , 2016, pp. 2091–2100
2091
Closest in time.

Beyond the bibliography

alphaXiv searches the wider corpus for related work and actual follow-ups.

Open on alphaXiv

alphaXiv is searching for related work…

Reading the bibliography…