Multi-level Matching Network for Multimodal Entity Linking

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Hu, Zhiwei, Gutiérrez-Basulto, Víctor, Li, Ru, Pan, Jeff Z.
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915063533666304
author Hu, Zhiwei
Gutiérrez-Basulto, Víctor
Li, Ru
Pan, Jeff Z.
author_facet Hu, Zhiwei
Gutiérrez-Basulto, Víctor
Li, Ru
Pan, Jeff Z.
contents Multimodal entity linking (MEL) aims to link ambiguous mentions within multimodal contexts to corresponding entities in a multimodal knowledge base. Most existing approaches to MEL are based on representation learning or vision-and-language pre-training mechanisms for exploring the complementary effect among multiple modalities. However, these methods suffer from two limitations. On the one hand, they overlook the possibility of considering negative samples from the same modality. On the other hand, they lack mechanisms to capture bidirectional cross-modal interaction. To address these issues, we propose a Multi-level Matching network for Multimodal Entity Linking (M3EL). Specifically, M3EL is composed of three different modules: (i) a Multimodal Feature Extraction module, which extracts modality-specific representations with a multimodal encoder and introduces an intra-modal contrastive learning sub-module to obtain better discriminative embeddings based on uni-modal differences; (ii) an Intra-modal Matching Network module, which contains two levels of matching granularity: Coarse-grained Global-to-Global and Fine-grained Global-to-Local, to achieve local and global level intra-modal interaction; (iii) a Cross-modal Matching Network module, which applies bidirectional strategies, Textual-to-Visual and Visual-to-Textual matching, to implement bidirectional cross-modal interaction. Extensive experiments conducted on WikiMEL, RichpediaMEL, and WikiDiverse datasets demonstrate the outstanding performance of M3EL when compared to the state-of-the-art baselines.
format Preprint
id arxiv_https___arxiv_org_abs_2412_10440
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Multi-level Matching Network for Multimodal Entity Linking
Hu, Zhiwei
Gutiérrez-Basulto, Víctor
Li, Ru
Pan, Jeff Z.
Computer Vision and Pattern Recognition
Artificial Intelligence
Multimodal entity linking (MEL) aims to link ambiguous mentions within multimodal contexts to corresponding entities in a multimodal knowledge base. Most existing approaches to MEL are based on representation learning or vision-and-language pre-training mechanisms for exploring the complementary effect among multiple modalities. However, these methods suffer from two limitations. On the one hand, they overlook the possibility of considering negative samples from the same modality. On the other hand, they lack mechanisms to capture bidirectional cross-modal interaction. To address these issues, we propose a Multi-level Matching network for Multimodal Entity Linking (M3EL). Specifically, M3EL is composed of three different modules: (i) a Multimodal Feature Extraction module, which extracts modality-specific representations with a multimodal encoder and introduces an intra-modal contrastive learning sub-module to obtain better discriminative embeddings based on uni-modal differences; (ii) an Intra-modal Matching Network module, which contains two levels of matching granularity: Coarse-grained Global-to-Global and Fine-grained Global-to-Local, to achieve local and global level intra-modal interaction; (iii) a Cross-modal Matching Network module, which applies bidirectional strategies, Textual-to-Visual and Visual-to-Textual matching, to implement bidirectional cross-modal interaction. Extensive experiments conducted on WikiMEL, RichpediaMEL, and WikiDiverse datasets demonstrate the outstanding performance of M3EL when compared to the state-of-the-art baselines.
title Multi-level Matching Network for Multimodal Entity Linking
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2412.10440