一句话：指出现有语义代码搜索模型未能充分利用代码图独特性，并探索更有效的代码图建模利用方式。
语义代码搜索能根据自然语言查询检索高度匹配的代码片段，从而促进软件复用。代码图（如控制流图、程序依赖图）具有丰富表达能力，因此多模态模型和预训练模型两类主流工作都尝试将代码图纳入代码建模。然而现有方法仍存在两点不足：一是搜索有效性仍有较大提升空间；二是没有充分考虑代码图的独有特性。该论文围绕“如何更好地利用代码图”这一问题展开，旨在改进语义代码搜索中对代码图的建模与利用。摘要未披露具体方法、模型细节及实验数据，因此关键结果尚不明确。
Semantic code search greatly facilitates software reuse, which enables users to find code snippets highly matching user-specified natural language queries. Due to the rich expressive power of code graphs (e.g., control-flow graph and program dependency graph), both of the two mainstream research works (i.e., multi-modal models and pre-trained models) have attempted to incorporate code graphs for code modelling. However, they still have some limitations: First, there is still much room for improvement in terms of search effectiveness. Second, they have not fully considered the unique features of code graphs.
@inproceedings{paperbot6984,
title = {How to better utilize code graphs in semantic code search?},
author = {Yucen Shi and Ying Yin and Zhengkui Wang and David Lo and Tao Zhang and Xin Xia and Yuhai Zhao and Bowen Xu},
booktitle = {FSE},
year = {2022},
doi = {10.1145/3540250.3549087}
}