Generalizability of Code Clone Detection on CodeBERT Article Swipe

PDF

Related Concepts

Generalizability theory Computer science clone (Java method) Benchmark (surveying) Code (set theory) Task (project management) Programming language Engineering Mathematics Biology Gene Set (abstract data type) Systems engineering Biochemistry Statistics Geography Geodesy

Tim Sonnekalb , Bernd Gruner , Clemens-Alexander Brust , Patrick Mäder ·

YOU? · · 2022 · Open Access · · DOI: https://doi.org/10.1145/3551349.3561165 · OA: W4313563720

Transformer networks such as CodeBERT already achieve outstanding results for code clone detection in benchmark datasets, so one could assume that this task has already been solved. However, code clone detection is not a trivial task. Semantic code clones, in particular, are challenging to detect. We show that the generalizability of CodeBERT decreases by evaluating two different subsets of Java code clones from BigCloneBench. We observe a significant drop in F1 score when we evaluate different code snippets and functionality IDs than those used for model building.