@article{ramamoorthy-etal-2026-merlin,
    title = "{MERLIN}: A Testbed for Multilingual Multimodal Entity Recognition and Linking",
    author = "Ramamoorthy, Sathyanarayanan  and
      Shah, Vishwa  and
      Khanuja, Simran  and
      Sheikh, Zaid  and
      Jie, Shan  and
      Chia, Ann  and
      Chua, Shearman  and
      Neubig, Graham",
    journal = "Transactions of the Association for Computational Linguistics",
    volume = "14",
    year = "2026",
    address = "Cambridge, MA",
    publisher = "MIT Press",
    url = "https://preview.aclanthology.org/ingest-latest-mitpress-cl-tacl/2026.tacl-1.19/",
    doi = "10.1162/tacl.a.633",
    pages = "399--417",
    abstract = "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 online.1"
}