Of Human Criteria and Automatic Metrics: A Benchmark of the Evaluation of Story Generation
Article Status
Published
Authors/contributors
- Chhun, Cyril (Author)
- Colombo, Pierre (Author)
- Clavel, Chloé (Author)
- Suchanek, Fabian M. (Author)
Title
Of Human Criteria and Automatic Metrics: A Benchmark of the Evaluation of Story Generation
Abstract
Research on Automatic Story Generation (ASG) relies heavily on human and automatic evaluation. However, there is no consensus on which human evaluation criteria to use, and no analysis of how well automatic criteria correlate with them. In this paper, we propose to re-evaluate ASG evaluation. We introduce a set of 6 orthogonal and comprehensive human criteria, carefully motivated by the social sciences literature. We also present HANNA, an annotated dataset of 1,056 stories produced by 10 different ASG systems. HANNA allows us to quantitatively evaluate the correlations of 72 automatic metrics with human criteria. Our analysis highlights the weaknesses of current metrics for ASG and allows us to formulate practical recommendations for ASG evaluation.
Repository
arXiv
Archive ID
arXiv:2208.11646
Date
2022-09-15
Accessed
19/04/2024, 16:44
Short Title
Of Human Criteria and Automatic Metrics
Library Catalogue
Extra
arXiv:2208.11646 [cs]
Citation
Chhun, C., Colombo, P., Clavel, C., & Suchanek, F. M. (2022). Of Human Criteria and Automatic Metrics: A Benchmark of the Evaluation of Story Generation (arXiv:2208.11646). arXiv. http://arxiv.org/abs/2208.11646
Technical methods
Link to this record