一句话：提出零样本学习用于自动程序修复，避免依赖大量高质量修复提交。
自动程序修复（APR）中，基于模板的方法受限于预定义模板，而基于深度学习的方法将 APR 视为神经机器翻译，依赖大量高质量缺陷修复提交，构建成本高且可能限制编辑多样性与上下文表示。本文提出通过零样本学习重新审视 APR，即在不进行（或极少）针对性训练的情况下完成修复，从而绕开对大规模修复提交的依赖。所给摘要未涉及具体方法与实验结果，但论文标题表明其核心是减少训练数据需求、提升修复的泛化能力。
Due to the promising future of Automated Program Repair (APR), researchers have proposed various APR techniques, including heuristic-based, template-based, and constraint-based techniques. Among such classic APR techniques, template-based techniques have been widely recognized as state of the art. However, such template-based techniques require predefined templates to perform repair, and their effectiveness is thus limited. To this end, researchers have leveraged the recent advances in Deep Learning to further improve APR. Such learning-based techniques typically view APR as a Neural Machine Translation problem, using the buggy/fixed code snippets as the source/target languages for translation. In this way, such techniques heavily rely on large numbers of high-quality bug-fixing commits, which can be extremely costly/challenging to construct and may limit their edit variety and context representation.
DOI 原文 ·
@inproceedings{paperbot6996,
title = {Less training, more repairing please: revisiting automated program repair via zero-shot learning},
author = {Chunqiu Steven Xia and Lingming Zhang},
booktitle = {FSE},
year = {2022},
doi = {10.1145/3540250.3549101}
}