Retrieval, Analogy, and Composition: A framework for Compositional Generalization in Image Captioning

Zhan Shi, Hui Liu, Martin Renqiang Min, Christopher Malon, Li Erran Li, Xiaodan Zhu


Abstract
Image captioning systems are expected to have the ability to combine individual concepts when describing scenes with concept combinations that are not observed during training. In spite of significant progress in image captioning with the help of the autoregressive generation framework, current approaches fail to generalize well to novel concept combinations. We propose a new framework that revolves around probing several similar image caption training instances (retrieval), performing analogical reasoning over relevant entities in retrieved prototypes (analogy), and enhancing the generation process with reasoning outcomes (composition). Our method augments the generation model by referring to the neighboring instances in the training set to produce novel concept combinations in generated captions. We perform experiments on the widely used image captioning benchmarks. The proposed models achieve substantial improvement over the compared baselines on both composition-related evaluation metrics and conventional image captioning metrics.
Anthology ID:
2021.findings-emnlp.171
Volume:
Findings of the Association for Computational Linguistics: EMNLP 2021
Month:
November
Year:
2021
Address:
Punta Cana, Dominican Republic
Venue:
Findings
SIG:
SIGDAT
Publisher:
Association for Computational Linguistics
Note:
Pages:
1990–2000
Language:
URL:
https://aclanthology.org/2021.findings-emnlp.171
DOI:
10.18653/v1/2021.findings-emnlp.171
Bibkey:
Cite (ACL):
Zhan Shi, Hui Liu, Martin Renqiang Min, Christopher Malon, Li Erran Li, and Xiaodan Zhu. 2021. Retrieval, Analogy, and Composition: A framework for Compositional Generalization in Image Captioning. In Findings of the Association for Computational Linguistics: EMNLP 2021, pages 1990–2000, Punta Cana, Dominican Republic. Association for Computational Linguistics.
Cite (Informal):
Retrieval, Analogy, and Composition: A framework for Compositional Generalization in Image Captioning (Shi et al., Findings 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.findings-emnlp.171.pdf
Video:
 https://aclanthology.org/2021.findings-emnlp.171.mp4
Data
COCO