CoCoNuT: Combining Context-Aware Neural Translation Models using Ensemble for Program Repair
Automated generate-and-validate (G&V) program repair techniques (APR) typically rely on hard-coded rules, thus only fixing bugs following specific fix patterns. These rules require a significant amount of manual effort to discover and are hard to adapt to different programming languages. To address these challenges, we propose CoCoNuT, a new G&V technique, which uses ensemble learning on a new context-aware neural machine translation (NMT) architecture to automatically fix bugs in multiple programming languages. To better represent the context of a bug, we introduce a new context-aware NMT architecture that represents the buggy source code and its surrounding context separately. CoCoNuT also takes advantage of the randomness in hyper-parameter tuning to build multiple models that fix different bugs and combine these models using ensemble learning. Our evaluation on six popular benchmarks for four programming languages shows that CoCoNuT fixes 499 bugs, including 329 bugs that were fixed by none of the 25 techniques we compared with.
Mon 20 JulDisplayed time zone: Tijuana, Baja California change
13:30 - 14:30
REPAIR AND DEBUGTechnical Papers at Zoom
Chair(s): Xuan Bach D. Le The University of Melbourne
Public Live Stream/Recording. Registered participants should join via the Zoom link distributed in Slack.
|Can Automated Program Repair Refine Fault Localization? A Unified Debugging Approach|
Yiling Lou Peking University, China, Ali Ghanbari Iowa State University, Xia Li Kennesaw State University, Lingming Zhang The University of Texas at Dallas, Haotian Zhang Ant Financial, Dan Hao Peking University, Lu Zhang Peking University, ChinaDOI Pre-print Media Attached
|Automated Repair of Feature Interaction Failures in Automated Driving Systems|
Raja Ben Abdessalem SnT Centre/University of Luxembourg, Annibale Panichella Delft University of Technology, Shiva Nejati University of Ottawa, Lionel C. Briand SnT Centre/University of Luxembourg, Thomas StifterDOI Pre-print
|CoCoNuT: Combining Context-Aware Neural Translation Models using Ensemble for Program Repair|
Thibaud Lutellier , Viet Hung Pham University of Waterloo, Lawrence Pang , Yitong Li , Moshi Wei , Lin Tan Purdue UniversityDOI Media Attached