Assessing and Improving Dataset and Evaluation Methodology in Deep Learning for Code Clone Detection.
Haiyang LiQing GaoShikun ZhangPublished in: ISSRE (2023)
Keyphrases
- clone detection
- evaluation methodology
- deep learning
- linux kernel
- software reuse
- string matching
- evaluation methods
- software systems
- unsupervised learning
- test set
- test collection
- source code
- machine learning
- evaluation measures
- evaluation metrics
- mental models
- weakly supervised
- benchmark datasets
- operating system
- software engineering
- query suggestion
- open source
- object recognition
- feature selection