Learning to Generate Corrective Patches using Neural Machine Translation
Preprint
Abstract
Bug fixing is generally a manually-intensive task. However, recent work has proposed the idea of automated program repair, which aims to repair (at least a subset of) bugs in different ways such as code mutation, etc. Following in the same line of work as automated bug repair, in this paper we aim to leverage past fixes to propose fixes of current/future bugs. Specifically, we propose Ratchet, a corrective patch generation system using neural machine translation. By learning corresponding pre-correction and post-correction code in past fixes with a neural sequence-to-sequence model, Ratchet is able to generate a fix code for a given bug-prone code query. We perform an empirical study with five open source projects, namely Ambari, Camel, Hadoop, Jetty and Wicket, to evaluate the effectiveness of Ratchet. Our findings show that Ratchet can generate syntactically valid statements 98.7% of the time, and achieve an F1-measure between 0.29 - 0.83 with respect to the actual fixes adopted in the code base. In addition, we perform a qualitative validation using 20 participants to see whether the generated statements can be helpful in correcting bugs. Our survey showed that Ratchet's output was considered to be helpful in fixing the bugs on many occasions, even if fix was not 100% correct.Keywords
All Related Versions
This publication has 71 references indexed in Scilit:
- Do automated program repair techniques repair hard and important bugs?Empirical Software Engineering, 2017
- Repairing Programs with Semantic Code Search (T)2015
- Learning to Generate Pseudo-Code from Source Code Using Statistical Machine Translation2015
- Irish: A Hidden Markov Model to detect coded information islands in free textScience of Computer Programming, 2015
- Measuring and modeling programming experienceEmpirical Software Engineering, 2013
- Mining software repair models for reasoning on the search space of automated program fixingEmpirical Software Engineering, 2013
- Leveraging program equivalence for adaptive program repair: Models and first results2013
- A study of repetitiveness of code changes in software evolution2013
- Fault-prone module detection using large-scale text features based on spam filteringEmpirical Software Engineering, 2009
- Multilayer feedforward networks are universal approximatorsNeural Networks, 1989