Optimal Transport Guided Correlation Assignment for Multimodal Entity Linking

Zefeng Zhang, Jiawei Sheng, Zhang Chuang, Liangyunzhi Liangyunzhi, Wenyuan Zhang, Siqi Wang, Tingwen Liu


Abstract
Multimodal entity linking (MEL) aims to link ambiguous mentions in multimodal contexts to entities in a multimodal knowledge graph. A pivotal challenge is to fully leverage multi-element correlations between mentions and entities to bridge modality gap and enable fine-grained semantic matching. Existing methods attempt several local correlative mechanisms, relying heavily on the automatically learned attention weights, which may over-concentrate on partial correlations. To mitigate this issue, we formulate the correlation assignment problem as an optimal transport (OT) problem, and propose a novel MEL framework, namely OT-MEL, with OT-guided correlation assignment. Thereby, we exploit the correlation between multimodal features to enhance multimodal fusion, and the correlation between mentions and entities to enhance fine-grained matching. To accelerate model prediction, we further leverage knowledge distillation to transfer OT assignment knowledge to attention mechanism. Experimental results show that our model significantly outperforms previous state-of-the-art baselines and confirm the effectiveness of the OT-guided correlation assignment.
Anthology ID:
2024.findings-acl.243
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:
4103–4117
Language:
URL:
https://preview.aclanthology.org/build-pipeline-with-new-library/2024.findings-acl.243/
DOI:
10.18653/v1/2024.findings-acl.243
Bibkey:
Cite (ACL):
Zefeng Zhang, Jiawei Sheng, Zhang Chuang, Liangyunzhi Liangyunzhi, Wenyuan Zhang, Siqi Wang, and Tingwen Liu. 2024. Optimal Transport Guided Correlation Assignment for Multimodal Entity Linking. In Findings of the Association for Computational Linguistics: ACL 2024, pages 4103–4117, Bangkok, Thailand. Association for Computational Linguistics.
Cite (Informal):
Optimal Transport Guided Correlation Assignment for Multimodal Entity Linking (Zhang et al., Findings 2024)
Copy Citation:
PDF:
https://preview.aclanthology.org/build-pipeline-with-new-library/2024.findings-acl.243.pdf