· 2020
CoCoNuT: combining context-aware neural translation models using ensemble for program repair
- 334citations
- 2020year
Short summary
CoCoNuT combines multiple neural machine translation models to automatically repair program bugs, overcoming limitations of rule-based methods.
AI-generated from the title and abstract; the full text is not read.
Key points
- Existing automated program repair (APR) techniques use hard-coded rules that are difficult to adapt and require manual effort.
- These rule-based methods are limited to fixing bugs that follow specific patterns.
- CoCoNuT is proposed as an ensemble method combining context-aware neural translation models for APR.
- The goal is to overcome the limitations of rule-based systems and improve adaptability across programming languages.
AI-generated from the title and abstract; the full text is not read.
Abstract
Automated generate-and-validate (GV) 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 it is hard to adapt these rules to different programming languages.
The authors' abstract, as published at the source., 2020 · DOI ↗
Continue with a free account
Ask the paper: 3 free questions a day about this paper; save it, get its citation, new summaries every day for your field. Takeaways are Premium.
Continue free on the webSign in with Google or Apple; no card needed. You come back to this paper.
On your phone:
Field: Software
SoftwareComputer Science