Themis: Towards Flexible and Interpretable NLG Evaluation.

Xinyu Hu Li Lin Mingqi Gao Xunjian Yin Xiaojun Wan

Published in: CoRR (2024)

Keyphrases

gold standard
data sets
natural language generation
evaluation methods
evaluation method

machine learning
real time
artificial intelligence
decision trees
search algorithm

preprocessing
multiresolution
probabilistic model
knowledge representation
empirical evaluation

information retrieval
evaluation metrics
real world
evaluation model
comparative evaluation