Optimal Transport Guided Correlation Assignment for Multimodal Entity Linking

TL;DR

This paper introduces OT-MEL, a novel framework for Multimodal Entity Linking that uses optimal transport to better leverage correlations between modalities, improving fine-grained semantic matching.

Contribution

The paper formulates correlation assignment as an optimal transport problem and integrates it into MEL, enhancing multimodal fusion and matching accuracy.

Findings

OT-MEL outperforms previous state-of-the-art methods.

Optimal transport improves correlation modeling between modalities.

Knowledge distillation accelerates model prediction.

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.