IMAGINE: An Imagination-Based Automatic Evaluation Metric for Natural Language Generation

Automatic evaluations for natural language generation (NLG) conventionally rely on token-level or embedding-level comparisons with the text references. This is different from human language processing, for which visual imagination often improves comprehension.

Data and Resources

Cite this as

Wanrong Zhu, Xin Eric Wang, An Yan, Miguel Eckstein, William Yang Wang (2024). Dataset: IMAGINE: An Imagination-Based Automatic Evaluation Metric for Natural Language Generation. https://doi.org/10.57702/6xb0q0i7

DOI retrieved: December 2, 2024

Additional Info

Field Value
Created December 2, 2024
Last update December 2, 2024
Defined In https://doi.org/10.48550/arXiv.2106.05970
Author Wanrong Zhu
More Authors
Xin Eric Wang
An Yan
Miguel Eckstein
William Yang Wang