Re-evaluating Automatic Metrics for Image Captioning

Mert Kilickaya, Aykut Erdem, Nazli Ikizler-Cinbis, Erkut Erdem


Abstract
The task of generating natural language descriptions from images has received a lot of attention in recent years. Consequently, it is becoming increasingly important to evaluate such image captioning approaches in an automatic manner. In this paper, we provide an in-depth evaluation of the existing image captioning metrics through a series of carefully designed experiments. Moreover, we explore the utilization of the recently proposed Word Mover’s Distance (WMD) document metric for the purpose of image captioning. Our findings outline the differences and/or similarities between metrics and their relative robustness by means of extensive correlation, accuracy and distraction based evaluations. Our results also demonstrate that WMD provides strong advantages over other metrics.
Anthology ID:
E17-1019
Volume:
Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 1, Long Papers
Month:
April
Year:
2017
Address:
Valencia, Spain
Venue:
EACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
199–209
Language:
URL:
https://aclanthology.org/E17-1019
DOI:
Bibkey:
Cite (ACL):
Mert Kilickaya, Aykut Erdem, Nazli Ikizler-Cinbis, and Erkut Erdem. 2017. Re-evaluating Automatic Metrics for Image Captioning. In Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 1, Long Papers, pages 199–209, Valencia, Spain. Association for Computational Linguistics.
Cite (Informal):
Re-evaluating Automatic Metrics for Image Captioning (Kilickaya et al., EACL 2017)
Copy Citation:
PDF:
https://preview.aclanthology.org/ingestion-script-update/E17-1019.pdf
Data
COCOFlickr30k