REO-Relevance, Extraness, Omission: A Fine-grained Evaluation for Image Captioning

Ming Jiang, Junjie Hu, Qiuyuan Huang, Lei Zhang, Jana Diesner, Jianfeng Gao

Abstract
Popular metrics used for evaluating image captioning systems, such as BLEU and CIDEr, provide a single score to gauge the system’s overall effectiveness. This score is often not informative enough to indicate what specific errors are made by a given system. In this study, we present a fine-grained evaluation method REO for automatically measuring the performance of image captioning systems. REO assesses the quality of captions from three perspectives: 1) Relevance to the ground truth, 2) Extraness of the content that is irrelevant to the ground truth, and 3) Omission of the elements in the images and human references. Experiments on three benchmark datasets demonstrate that our method achieves a higher consistency with human judgments and provides more intuitive evaluation results than alternative metrics.
Anthology ID:
D19-1156
Volume:
Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)
Month:
November
Year:
2019
Address:
Hong Kong, China
Editors:
Kentaro Inui, Jing Jiang, Vincent Ng, Xiaojun Wan
Venues:
EMNLP | IJCNLP
SIG:
SIGDAT
Publisher:
Association for Computational Linguistics
Note:
Pages:
1475–1480
Language:
URL:
https://aclanthology.org/D19-1156
DOI:
10.18653/v1/D19-1156
Bibkey:
Cite (ACL):
Ming Jiang, Junjie Hu, Qiuyuan Huang, Lei Zhang, Jana Diesner, and Jianfeng Gao. 2019. REO-Relevance, Extraness, Omission: A Fine-grained Evaluation for Image Captioning. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), pages 1475–1480, Hong Kong, China. Association for Computational Linguistics.
Cite (Informal):
REO-Relevance, Extraness, Omission: A Fine-grained Evaluation for Image Captioning (Jiang et al., EMNLP-IJCNLP 2019)
Copy Citation:
PDF:
https://preview.aclanthology.org/add_acl24_videos/D19-1156.pdf
Code
 SeleenaJM/CapEval
PDF Search Code