一句话：提出重叠感知的代码检索方法 OCoR，利用名称与自然语言词之间的重叠关系提升检索效果。
该论文关注代码检索任务：给定自然语言描述，从代码片段集合中检索最相关的代码，以帮助开发者复用开源代码。现有基于神经网络的方法虽已成为主流，但未能捕捉一个重要特征——重叠。重叠有两类：不同人对同一概念可能使用不同名称，这些名称之间的重叠暗示潜在关联，例如“message”与“msg”；代码标识符与自然语言描述中的词语之间的重叠也暗示代码片段与描述可能相关。OCoR 将上述重叠作为潜在关联信号纳入代码检索。摘要主要阐述问题与动机，未报告具体数据集、评价指标或量化实验结果。
Code retrieval helps developers reuse code snippets in the open-source projects. Given a natural language description, code retrieval aims to search for the most relevant code relevant among a set of code snippets. Existing state-of-the-art approaches apply neural networks to code retrieval. However, these approaches still fail to capture an important feature: overlaps. The overlaps between different names used by different people indicate that two different names may be potentially related (e.g., "message" and "msg"), and the overlaps between identifiers in code and words in natural language descriptions indicate that the code snippet and the description may potentially be related.
DOI 原文 ·
@inproceedings{paperbot5967,
title = {OCoR},
author = {Qihao Zhu and Zeyu Sun and Xiran Liang and Yingfei Xiong and Lu Zhang},
booktitle = {ASE},
year = {2020},
doi = {10.1145/3324884.3416530}
}