The Role of Syntactic Planning in Compositional Image Captioning

Emanuele Bugliarello, Desmond Elliott


Abstract
Image captioning has focused on generalizing to images drawn from the same distribution as the training set, and not to the more challenging problem of generalizing to different distributions of images. Recently, Nikolaus et al. (2019) introduced a dataset to assess compositional generalization in image captioning, where models are evaluated on their ability to describe images with unseen adjective–noun and noun–verb compositions. In this work, we investigate different methods to improve compositional generalization by planning the syntactic structure of a caption. Our experiments show that jointly modeling tokens and syntactic tags enhances generalization in both RNN- and Transformer-based models, while also improving performance on standard metrics.
Anthology ID:
2021.eacl-main.48
Volume:
Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume
Month:
April
Year:
2021
Address:
Online
Venue:
EACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
593–607
Language:
URL:
https://aclanthology.org/2021.eacl-main.48
DOI:
10.18653/v1/2021.eacl-main.48
Bibkey:
Cite (ACL):
Emanuele Bugliarello and Desmond Elliott. 2021. The Role of Syntactic Planning in Compositional Image Captioning. In Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume, pages 593–607, Online. Association for Computational Linguistics.
Cite (Informal):
The Role of Syntactic Planning in Compositional Image Captioning (Bugliarello & Elliott, EACL 2021)
Copy Citation:
PDF:
https://preview.aclanthology.org/ingestion-script-update/2021.eacl-main.48.pdf
Code
 e-bug/syncap
Data
COCO