Why We Need New Evaluation Metrics for NLG.
Jekaterina NovikovaOndrej DusekAmanda Cercas CurryVerena RieserPublished in: EMNLP (2017)
Keyphrases
- evaluation metrics
- natural language generation
- precision and recall
- average precision
- evaluation methods
- natural language
- learning to rank
- evaluation methodology
- evaluation framework
- evaluation measures
- text generation
- information extraction
- natural language processing
- data sets
- similarity measure
- probabilistic model