Why We Need New Evaluation Metrics for NLG.

Jekaterina Novikova Ondrej Dusek Amanda Cercas Curry Verena Rieser

Published in: CoRR (2017)

Keyphrases

evaluation metrics
natural language generation
precision and recall
average precision
natural language
evaluation methods
text generation
learning to rank
evaluation framework
evaluation measures
evaluation methodology
data sets
web pages
query processing
co occurrence