Ukrainian Visual Word Sense Disambiguation

@inproceedings{laba-hryniv-2026-sparse,
    title = "From Sparse to Sense-Grounded: {W}ikipedia Training for {U}krainian Visual-{WSD}",
    author = "Laba, Yurii  and
      Hryniv, Rostyslav O.",
    editor = "Bonial, Claire  and
      Berzak, Yevgeni",
    booktitle = "Proceedings of the 30th Conference on Computational Natural Language Learning",
    month = jul,
    year = "2026",
    address = "San Diego, California, USA",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2026.conll-main.29/",
    doi = "10.18653/v1/2026.conll-main.29",
    pages = "501--514",
    ISBN = "979-8-89176-410-1",
    abstract = "Visual Word Sense Disambiguation (Visual-WSD) requires ranking the correct image for an ambiguous word given a short trigger phrase. For low-resource languages, it is bottle{\-}necked by scarce sense-level benchmarks and limited sense-aligned multimodal supervision.
We study Ukrainian and (i) extend the Ukrainian Visual-WSD benchmark from 87 to 381 instances and benchmark multilingual CLIP checkpoints and multimodal large models, and (ii) introduce two scalable Wikipedia-derived dataset construction methods. Using compute-efficient adaptation we fine-tune a multilingual CLIP backbone and show that sense-grounded supervision drives the improvements: combining our two Wikipedia-derived datasets improves HIT@1 from 37.00{\%} to 43.05{\%}."
}

@inproceedings{laba-etal-2024-ukrainian,
    title = "{U}krainian Visual Word Sense Disambiguation Benchmark",
    author = "Laba, Yurii  and
      Mohytych, Yaryna  and
      Rohulia, Ivanna  and
      Kyryleyza, Halyna  and
      Dydyk-Meush, Hanna  and
      Dobosevych, Oles  and
      Hryniv, Rostyslav",
    editor = "Romanyshyn, Mariana  and
      Romanyshyn, Nataliia  and
      Hlybovets, Andrii  and
      Ignatenko, Oleksii",
    booktitle = "Proceedings of the Third Ukrainian Natural Language Processing Workshop (UNLP) @ LREC-COLING 2024",
    month = may,
    year = "2024",
    address = "Torino, Italia",
    publisher = "ELRA and ICCL",
    url = "https://aclanthology.org/2024.unlp-1.8/",
    doi = "10.63317/3pn6eqt8c2n9",
    pages = "61--66",
    ISBN = "978-2-493814-43-2",
    abstract = "This study presents a benchmark for evaluating the Visual Word Sense Disambiguation (Visual-WSD) task in Ukrainian. The main goal of the Visual-WSD task is to identify, with minimal contextual information, the most appropriate representation of a given ambiguous word from a set of ten images. To construct this benchmark, we followed a methodology similar to that proposed by (CITATION), who previously introduced benchmarks for the Visual-WSD task in English, Italian, and Farsi.
This approach allows us to incorporate the Ukrainian benchmark into a broader framework for cross-language model performance comparisons. We collected the benchmark data semi-automatically and refined it with input from domain experts. We then assessed eight multilingual and multimodal large language models using this benchmark. All tested models performed worse than the zero-shot CLIP-based baseline model (CITATION) used by (CITATION) for the English Visual-WSD task.
Our analysis revealed a significant performance gap in the Visual-WSD task between Ukrainian and English."
}