On conducting better validation studies of automatic metrics in natural language generation evaluation.
Johnny Tian-Zheng WeiPublished in: CoRR (2019)
Keyphrases
- natural language generation
- evaluation metrics
- text generation
- evaluation methods
- automatic evaluation
- dialog systems
- machine translation
- natural language
- aggregated search
- dialogue system
- evaluation measures
- dialogue management
- natural language processing
- information extraction
- evaluation criteria
- evaluation method
- evaluation methodology
- semi automatic
- data mining