Abstract
Code search is an important approach to improve effectiveness and efficiency of software development. The current studies commonly search target code based on either semantic or statistical information in large datasets. Semantic and statistical information have hidden relationships between them since they describe code snippets from different perspectives. In this work, we propose a joint embedding model of semantic and statistical features to improve the effectiveness of code annotation. Then, we implement a code search engine, i.e., JessCS, based on the joint embedding model. We evaluate JessCS on more than 1 million lines of code snippets and corresponding descriptions. The experimental results show that JessCS performs more effective than UNIF-based approach, with at least 13% improvements on the studied metrics.
Subject
Fluid Flow and Transfer Processes,Computer Science Applications,Process Chemistry and Technology,General Engineering,Instrumentation,General Materials Science
Reference42 articles.
1. A study of the uniqueness of source code;Gabel;Proceedings of the 18th ACM SIGSOFT International Symposium on Foundations of Software Engineering,2010
2. Adam: A Method for Stochastic Optimization;Kingma;Proceedings of the 3rd International Conference on Learning Representations,2015
3. Incorporating Code Structure and Quality in Deep Code Search
4. Deep code search;Gu;Proceedings of the 40th International Conference on Software Engineering. ACM,2018
5. Cross-language code search using static and dynamic analyses;Mathew;Proceedings of the 29th ACM Joint European Software Engineering Conference and Symposium on the Foundations of Software Engineering,2021