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
Venues:
EMNLP | IJCNLP
SIG:
SIGDAT
Publisher:
Association for Computational Linguistics
Note:
Pages:
1475–1480
URL:
https://www.aclweb.org/anthology/D19-1156
DOI:
10.18653/v1/D19-1156
Bib Export formats:
BibTeX MODS XML EndNote
PDF:
https://www.aclweb.org/anthology/D19-1156.pdf