Structural-semantics Guided Program Simplification for Understanding Neural Code Intelligence Models
Chaoxuan Shi, Tingwei Zhu, Tian Zhang, Jun Pang, Minxue Pan · 2023
Neural code intelligence models are cutting-edge automated code understanding technologies that have achieved remarkable performance in various software engineering tasks. However, the lack of deep learning models’ interpretability hinders the application of deep learning based code intelligence models in real-world scenarios, particularly in security-critical domains. Previous studies use program simplification to understand neural code intelligence models, but they have overlooked the fact that the most significant difference between source code and natural language is the code’s structural semantics.