# Learning to Generate Corrective Patches using Neural Machine Translation

arXiv: https://arxiv.org/abs/1812.07170 · HTML: https://mlsanity.com/paper/1812.07170/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 18 Dec 2018.

## Built on by (most cited first, 10 of 10)

- [A Syntax-Guided Edit Decoder for Neural Program Repair](https://mlsanity.com/paper/2106.08253/) (2021)
- [Deep Learning for Code Intelligence: Survey, Benchmark and Toolkit](https://mlsanity.com/paper/2401.00288/) (2023)
- [Shellcode_IA32: A Dataset for Automatic Shellcode Generation](https://mlsanity.com/paper/2104.13100/) (2021)
- [Revisiting and Improving Retrieval-Augmented Deep Assertion Generation](https://mlsanity.com/paper/2309.10264/) (2023)
- [A Survey on Artificial Intelligence for Source Code: A Dialogue Systems Perspective](https://mlsanity.com/paper/2202.04847/) (2022)
- [Program Repair with Minimal Edits Using CodeT5](https://mlsanity.com/paper/2309.14760/) (2023)
- [Leveraging Causal Inference for Explainable Automatic Program Repair](https://mlsanity.com/paper/2205.13342/) (2022)
- [The Rise and Fall(?) of Software Engineering](https://mlsanity.com/paper/2406.10141/) (2024)
- [Code Sophistication: From Code Recommendation to Logic Recommendation](https://mlsanity.com/paper/2201.07674/) (2022)
- [Can We Generate Shellcodes via Natural Language? An Empirical Study](https://mlsanity.com/paper/2202.03755/) (2022)

## Abstract (arXiv)

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.