Cross-modal Coherence Modeling for Caption Generation

Malihe Alikhani, Piyush Sharma, Shengjie Li, Radu Soricut, Matthew Stone


Abstract
We use coherence relations inspired by computational models of discourse to study the information needs and goals of image captioning. Using an annotation protocol specifically devised for capturing image–caption coherence relations, we annotate 10,000 instances from publicly-available image–caption pairs. We introduce a new task for learning inferences in imagery and text, coherence relation prediction, and show that these coherence annotations can be exploited to learn relation classifiers as an intermediary step, and also train coherence-aware, controllable image captioning models. The results show a dramatic improvement in the consistency and quality of the generated captions with respect to information needs specified via coherence relations.
Anthology ID:
2020.acl-main.583
Volume:
Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics
Month:
July
Year:
2020
Address:
Online
Editors:
Dan Jurafsky, Joyce Chai, Natalie Schluter, Joel Tetreault
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
6525–6535
Language:
URL:
https://aclanthology.org/2020.acl-main.583
DOI:
10.18653/v1/2020.acl-main.583
Bibkey:
Cite (ACL):
Malihe Alikhani, Piyush Sharma, Shengjie Li, Radu Soricut, and Matthew Stone. 2020. Cross-modal Coherence Modeling for Caption Generation. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 6525–6535, Online. Association for Computational Linguistics.
Cite (Informal):
Cross-modal Coherence Modeling for Caption Generation (Alikhani et al., ACL 2020)
Copy Citation:
PDF:
https://preview.aclanthology.org/nschneid-patch-2/2020.acl-main.583.pdf
Software:
 2020.acl-main.583.Software.zip
Dataset:
 2020.acl-main.583.Dataset.tsv
Video:
 http://slideslive.com/38929201