How to better utilize code graphs in semantic code search?
Yucen Shi, Ying Yin, Zhengkui Wang, David Lo, Tao Zhang, Xin Xia, Yuhai Zhao, Bowen Xu · Proceedings of the 30th ACM Joint European Software Engineering Conference and Symposium on the Foundations of Software Engineering · 2022
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.