CodeXGLUE: A Machine Learning Benchmark Dataset for Code Understanding and Generation.
Shuai LuDaya GuoShuo RenJunjie HuangAlexey SvyatkovskiyAmbrosio BlancoColin B. ClementDawn DrainDaxin JiangDuyu TangGe LiLidong ZhouLinjun ShouLong ZhouMichele TufanoMing GongMing ZhouNan DuanNeel SundaresanShao Kun DengShengyu FuShujie LiuPublished in: CoRR (2021)
Keyphrases
- benchmark datasets
- machine learning
- computer vision
- knowledge acquisition
- learning algorithm
- ensemble methods
- pedestrian detection
- knowledge discovery
- natural language processing
- data mining
- machine learning algorithms
- machine learning methods
- learning systems
- information extraction
- computer science
- semi supervised learning
- model selection
- source code
- text mining
- learning tasks
- machine learning approaches
- future development
- machine learning and data mining
- generation process
- deeper understanding
- generation method
- terms of classification accuracy