Light Up the Shadows: Enhance Long-Tailed Entity Grounding with Concept-Guided Vision-Language Models

Yikai Zhang, Qianyu He, Xintao Wang, Siyu Yuan, Jiaqing Liang, Yanghua Xiao


Abstract
Multi-Modal Knowledge Graphs (MMKGs) have proven valuable for various downstream tasks. However, scaling them up is challenging because building large-scale MMKGs often introduces mismatched images (i.e., noise). Most entities in KGs belong to the long tail, meaning there are few images of them available online. This scarcity makes it difficult to determine whether a found image matches the entity. To address this, we draw on the Triangle of Reference Theory and suggest enhancing vision-language models with concept guidance. Specifically, we introduce COG, a two-stage framework with COncept-Guided vision-language models. The framework comprises a Concept Integration module, which effectively identifies image-text pairs of long-tailed entities, and an Evidence Fusion module, which offers explainability and enables human verification. To demonstrate the effectiveness of COG, we create a dataset of 25k image-text pairs of long-tailed entities. Our comprehensive experiments show that COG not only improves the accuracy of recognizing long-tailed image-text pairs compared to baselines but also offers flexibility and explainability.
Anthology ID:
2024.findings-acl.793
Volume:
Findings of the Association for Computational Linguistics: ACL 2024
Month:
August
Year:
2024
Address:
Bangkok, Thailand
Editors:
Lun-Wei Ku, Andre Martins, Vivek Srikumar
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
13379–13389
Language:
URL:
https://aclanthology.org/2024.findings-acl.793
DOI:
10.18653/v1/2024.findings-acl.793
Bibkey:
Cite (ACL):
Yikai Zhang, Qianyu He, Xintao Wang, Siyu Yuan, Jiaqing Liang, and Yanghua Xiao. 2024. Light Up the Shadows: Enhance Long-Tailed Entity Grounding with Concept-Guided Vision-Language Models. In Findings of the Association for Computational Linguistics: ACL 2024, pages 13379–13389, Bangkok, Thailand. Association for Computational Linguistics.
Cite (Informal):
Light Up the Shadows: Enhance Long-Tailed Entity Grounding with Concept-Guided Vision-Language Models (Zhang et al., Findings 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.findings-acl.793.pdf