# A Dual-way Enhanced Framework from Text Matching Point of View for Multimodal Entity Linking

arXiv: https://arxiv.org/abs/2312.11816 · HTML: https://mlsanity.com/paper/2312.11816/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- Builds on 12 of its 39 references that are in the map.
- First posted on arXiv 19 Dec 2023.

## Builds on (most cited first, 12 of 12)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Hierarchical Question-Image Co-Attention for Visual Question Answering](https://mlsanity.com/paper/1606.00061/) (2016)
- [Mean-Shifted Contrastive Loss for Anomaly Detection](https://mlsanity.com/paper/2106.03844/) (2021)
- [WikiDiverse: A Multimodal Entity Linking Dataset with Diversified Contextual Topics and Entity Types](https://mlsanity.com/paper/2204.06347/) (2022)
- [Multimodal Entity Linking for Tweets](https://mlsanity.com/paper/2104.03236/) (2021)
- [Scene Graph as Pivoting: Inference-time Image-free Unsupervised Multimodal Machine Translation with Visual Scene Hallucination](https://mlsanity.com/paper/2305.12256/) (2023)
- [Named Entity Disambiguation for Noisy Text](https://mlsanity.com/paper/1706.09147/) (2017)
- [ITA: Image-Text Alignments for Multi-Modal Named Entity Recognition](https://mlsanity.com/paper/2112.06482/) (2021)
- [Few-shot Named Entity Recognition with Self-describing Networks](https://mlsanity.com/paper/2203.12252/) (2022)
- [Visual Named Entity Linking: A New Dataset and A Baseline](https://mlsanity.com/paper/2211.04872/) (2022)

## Built on by (most cited first, 12 of 12)

- [Knowledge Graphs Meet Multi-Modal Learning: A Comprehensive Survey](https://mlsanity.com/paper/2402.05391/) (2024)
- [MMGraphRAG: Bridging Vision and Language with Interpretable Multimodal Knowledge Graphs](https://mlsanity.com/paper/2507.20804/) (2025)
- [UniMEL: A Unified Framework for Multimodal Entity Linking with Large Language Models](https://mlsanity.com/paper/2407.16160/) (2024)
- [KGMEL: Knowledge Graph-Enhanced Multimodal Entity Linking](https://mlsanity.com/paper/2504.15135/) (2025)
- [Enhancing Multimodal Entity Linking with Jaccard Distance-based Conditional Contrastive Learning and Contextual Visual Augmentation](https://mlsanity.com/paper/2501.14166/) (2025)
- [DeepMEL: A Multi-Agent Collaboration Framework for Multimodal Entity Linking](https://mlsanity.com/paper/2508.15876/) (2025)
- [DWE+: Dual-Way Matching Enhanced Framework for Multimodal Entity Linking](https://mlsanity.com/paper/2404.04818/) (2024)
- [DIM: Dynamic Integration of Multimodal Entity Linking with Large Language Model](https://mlsanity.com/paper/2407.12019/) (2024)
- [VP-MEL: Visual Prompts Guided Multimodal Entity Linking](https://mlsanity.com/paper/2412.06720/) (2024)
- [Multi-level Mixture of Experts for Multimodal Entity Linking](https://mlsanity.com/paper/2507.07108/) (2025)
- [I2CR: Intra- and Inter-modal Collaborative Reflections for Multimodal Entity Linking](https://mlsanity.com/paper/2508.02243/) (2025)
- [KARAMEL: Knowledge-Aware Ranking for Multimodal Entity Linking in the Arts via Heterogeneous Graphs](https://mlsanity.com/paper/2610.16502/) (2026)

## Abstract (arXiv)

Multimodal Entity Linking (MEL) aims at linking ambiguous mentions with multimodal information to entity in Knowledge Graph (KG) such as Wikipedia, which plays a key role in many applications. However, existing methods suffer from shortcomings, including modality impurity such as noise in raw image and ambiguous textual entity representation, which puts obstacles to MEL. We formulate multimodal entity linking as a neural text matching problem where each multimodal information (text and image) is treated as a query, and the model learns the mapping from each query to the relevant entity from candidate entities. This paper introduces a dual-way enhanced (DWE) framework for MEL: (1) our model refines queries with multimodal data and addresses semantic gaps using cross-modal enhancers between text and image information. Besides, DWE innovatively leverages fine-grained image attributes, including facial characteristic and scene feature, to enhance and refine visual features. (2)By using Wikipedia descriptions, DWE enriches entity semantics and obtains more comprehensive textual representation, which reduces between textual representation and the entities in KG. Extensive experiments on three public benchmarks demonstrate that our method achieves state-of-the-art (SOTA) performance, indicating the superiority of our model. The code is released on https://github.com/season1blue/DWE