mlsanityData to 7 Oct 2026

MERLIN: A Testbed for Multilingual Multimodal Entity Recognition and Linking

arXiv 2510.14307 ↗First posted 16 Oct 2025cs.CL cs.AIcited by 1

Not on the map. Why?

Abstract (arXiv)

This paper introduces MERLIN, a novel testbed system for the task of Multilingual Multimodal Entity Linking. The created dataset includes BBC news article titles, paired with corresponding images, in five languages: Hindi, Japanese, Indonesian, Vietnamese, and Tamil, featuring over 7,000 named entity mentions linked to 2,500 unique Wikidata entities. We also include several benchmarks using multilingual and multimodal entity linking methods exploring different language models like LLaMa-2 and Aya-23. Our findings indicate that incorporating visual data improves the accuracy of entity linking, especially for entities where the textual context is ambiguous or insufficient, and particularly for models that do not have strong multilingual abilities. For the work, the dataset, methods are available here at https://github.com/rsathya4802/merlin

Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 25 of its 41 references that are in the map. First posted on arXiv 16 Oct 2025.

Builds on

25 of 41 references.

References · 25

  1. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 12,865
  2. 2022No Language Left Behind: Scaling Human-Centered Machine Translationcited by 1,290
  3. 2020The State and Fate of Linguistic Diversity and Inclusion in the NLP Worldcited by 789
  4. 2020Autoregressive Entity Retrievalcited by 333
  5. 2019Zero-Shot Entity Linking by Reading Entity Descriptionscited by 124
  6. 2024Aya 23: Open Weight Releases to Further Multilingual Progresscited by 121
  7. 2021Systematic Inequalities in Language Technology Performance across the World's Languagescited by 118
  8. 2020Entities as Experts: Sparse Memory Access with Entity Supervisioncited by 100
  9. 2018Question Answering by Reasoning Across Documents with Graph Convolutional Networkscited by 56
  10. 2020Entity Linking in 100 Languagescited by 52
  11. 2023Large Multilingual Models Pivot Zero-Shot Multimodal Learning across Languagescited by 52
  12. 2021Multilingual Autoregressive Entity Linkingcited by 50
13 more
  1. 2022WikiDiverse: A Multimodal Entity Linking Dataset with Diversified Contextual Topics and Entity Typescited by 33
  2. 2021Multimodal Entity Linking for Tweetscited by 28
  3. 2022Knowledge Graph Augmented Network Towards Multiview Representation Learning for Aspect-based Sentiment Analysiscited by 16
  4. 2023Large Scale Multi-Lingual Multi-Modal Summarization Datasetcited by 12
  5. 2023Generative Multimodal Entity Linkingcited by 11
  6. 2020Improving Candidate Generation for Low-resource Cross-lingual Entity Linkingcited by 10
  7. 2022Improving Candidate Retrieval with Entity Profile Generation for Wikidata Entity Linkingcited by 10
  8. 2023AMELI: Enhancing Multimodal Entity Linking with Fine-Grained Attributescited by 8
  9. 2023Multilingual End to End Entity Linkingcited by 8
  10. 2023DRIN: Dynamic Relation Interactive Network for Multimodal Entity Linkingcited by 8
  11. 2017One for All: Towards Language Independent Named Entity Linkingcited by 5
  12. 2024DWE+: Dual-Way Matching Enhanced Framework for Multimodal Entity Linkingcited by 2
  13. 20242M-NER: Contrastive Learning for Multilingual and Multimodal NER with Language and Modal Fusioncited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026Think Before You Link: Rarity, Reasoning, and Retrieval in Multilingual Entity Linkingcited by 0