Are NLP Metrics Suitable for Evaluating Generated Code?
Riku TakaichiYoshiki HigoShinsuke MatsumotoShinji KusumotoToshiyuki KurabayashiHiroyuki KirinukiHaruto TannoPublished in: PROFES (2022)
Keyphrases
- natural language processing
- natural language
- text mining
- source code
- databases
- information extraction
- error metrics
- natural language understanding
- similarity metrics
- generation process
- error correction
- evaluation metrics
- automatically generated
- question answering
- feature selection
- information systems
- machine learning