mlsanityData to 7 Oct 2026

Multimodal Entity Linking for Tweets

arXiv 2104.03236 ↗First posted 7 Apr 2021cs.IR cs.CL cs.MMcited by 28

Not on the map. Why?

Abstract (arXiv)

In many information extraction applications, entity linking (EL) has emerged as a crucial task that allows leveraging information about named entities from a knowledge base. In this paper, we address the task of multimodal entity linking (MEL), an emerging research field in which textual and visual information is used to map an ambiguous mention to an entity in a knowledge base (KB). First, we propose a method for building a fully annotated Twitter dataset for MEL, where entities are defined in a Twitter KB. Then, we propose a model for jointly learning a representation of both mentions and entities from their textual and visual contexts. We demonstrate the effectiveness of the proposed model by evaluating it on the proposed dataset and highlight the importance of leveraging visual information when it is available.

Key facts. Cited by 28 papers in the map (data through 7 Oct 2026). Builds on 20 of its 50 references that are in the map. First posted on arXiv 7 Apr 2021.

Builds on

20 of 50 references.

References · 20

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  2. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,441
  3. 2016Layer Normalizationcited by 5,579
  4. 2015Rethinking the Inception Architecture for Computer Visioncited by 5,451
  5. 2013Efficient Estimation of Word Representations in Vector Spacecited by 4,346
  6. 2015VQA: Visual Question Answeringcited by 2,489
  7. 2018Deep contextualized word representationscited by 2,285
  8. 2015Aligning Books and Movies: Towards Story-like Visual Explanations by Watching Movies and Reading Bookscited by 1,041
  9. 2014Deep Visual-Semantic Alignments for Generating Image Descriptionscited by 966
  10. 2017Supervised Learning of Universal Sentence Representations from Natural Language Inference Datacited by 428
  11. 2016FastText.zip: Compressing text classification modelscited by 331
  12. 2015Skip-Thought Vectorscited by 321
8 more
  1. 2013One Billion Word Benchmark for Measuring Progress in Statistical Language Modelingcited by 302
  2. 2016Multimodal Compact Bilinear Pooling for Visual Question Answering and Visual Groundingcited by 243
  3. 2015DenseCap: Fully Convolutional Localization Networks for Dense Captioningcited by 176
  4. 2015Learning Deep Structure-Preserving Image-Text Embeddingscited by 139
  5. 2017Learning Two-Branch Neural Networks for Image-Text Matching Taskscited by 119
  6. 2017Unsupervised Learning of Sentence Embeddings using Compositional n-Gram Featurescited by 103
  7. 2017Named Entity Disambiguation for Noisy Textcited by 24
  8. 2018Webly Supervised Joint Embedding for Cross-Modal Image-Text Retrievalcited by 10

Built on by

Cited by year

Citing papers per year: 2021: 2; 2022: 5; 2023: 7; 2024: 8; 2025: 6.

28 papers.

Sort:

By area:

  1. 2022Multi-Modal Knowledge Graph Construction and Application: A Surveycited by 74
  2. 2022WikiDiverse: A Multimodal Entity Linking Dataset with Diversified Contextual Topics and Entity Typescited by 33
  3. 2021Entity Linking Meets Deep Learning: Techniques and Solutionscited by 21
  4. 2022Visual Named Entity Linking: A New Dataset and A Baselinecited by 15
  5. 2023Multi-Grained Multimodal Interaction Network for Entity Linkingcited by 12
  6. 2023Generative Multimodal Entity Linkingcited by 11
  7. 2023A Dual-way Enhanced Framework from Text Matching Point of View for Multimodal Entity Linkingcited by 11
  8. 2022Kuaipedia: a Large-scale Multi-modal Short-video Encyclopediacited by 8
  9. 2023AMELI: Enhancing Multimodal Entity Linking with Fine-Grained Attributescited by 8
  10. 2023DRIN: Dynamic Relation Interactive Network for Multimodal Entity Linkingcited by 8
  11. 2023Benchmarking Diverse-Modal Entity Linking with Generative Modelscited by 5
  12. 2024Optimal Transport Guided Correlation Assignment for Multimodal Entity Linkingcited by 5
16 more
  1. 2024UniMEL: A Unified Framework for Multimodal Entity Linking with Large Language Modelscited by 4
  2. 2023Evaluating end-to-end entity linking on domain-specific knowledge bases: Learning about ancient technologies from museum collectionscited by 3
  3. 2025KGMEL: Knowledge Graph-Enhanced Multimodal Entity Linkingcited by 3
  4. 2025DeepMEL: A Multi-Agent Collaboration Framework for Multimodal Entity Linkingcited by 3
  5. 2022Learning Semantic Ambiguities for Zero-Shot Learningcited by 2
  6. 2024DWE+: Dual-Way Matching Enhanced Framework for Multimodal Entity Linkingcited by 2
  7. 2024Multi-level Matching Network for Multimodal Entity Linkingcited by 2
  8. 2021Multimodal Entity Tagging with Multimodal Knowledge Basecited by 1
  9. 2024OVEL: Large Language Model as Memory Manager for Online Video Entity Linkingcited by 1
  10. 2024Exploring Large Language Models for Multimodal Sentiment Analysis: Challenges, Benchmarks, and Future Directionscited by 1
  11. 2025MERLIN: A Testbed for Multilingual Multimodal Entity Recognition and Linkingcited by 1
  12. 2024DIM: Dynamic Integration of Multimodal Entity Linking with Large Language Modelcited by 0
  13. 2024VP-MEL: Visual Prompts Guided Multimodal Entity Linkingcited by 0
  14. 2025Multi-level Mixture of Experts for Multimodal Entity Linkingcited by 0
  15. 2025I2CR: Intra- and Inter-modal Collaborative Reflections for Multimodal Entity Linkingcited by 0
  16. 2025PGMEL: Policy Gradient-based Generative Adversarial Network for Multimodal Entity Linkingcited by 0