@inproceedings{pena-gnecco-etal-2025-verbanexai,
    title = "{V}erba{N}ex{AI} at {S}em{E}val-2025 Task 2: Enhancing Entity-Aware Translation with {W}ikidata-Enriched {M}arian{MT}",
    author = "Pe{\~n}a Gnecco, Daniel  and
      Martinez Santos, Juan Carlos  and
      Puertas, Edwin",
    editor = "Rosenthal, Sara  and
      Ros{\'a}, Aiala  and
      Ghosh, Debanjan  and
      Zampieri, Marcos",
    booktitle = "Proceedings of the 19th International Workshop on Semantic Evaluation (SemEval-2025)",
    month = jul,
    year = "2025",
    address = "Vienna, Austria",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/transition-to-people-yaml/2025.semeval-1.167/",
    pages = "1255--1262",
    ISBN = "979-8-89176-273-2",
    abstract = "This paper presents the VerbaNexAi Lab system for SemEval-2025 Task 2: Entity-Aware Machine Translation (EA-MT), focusing on translating named entities from English to Spanish across categories such as musical works, foods, and landmarks. Our approach integrates detailed data preprocessing, enrichment with 240,432 Wikidata entity pairs, and fine-tuning of the MarianMT model to enhance entity translation accuracy. Official results reveal a COMET score of 87.09, indicating high fluency, an M-ETA score of 24.62, highlighting challenges in entity precision, and an Overall Score of 38.38, ranking last among 34 systems. While Wikidata improved translations for common entities like ``{\'A}guila de San Juan,'' our static methodology underperformed compared to dynamic LLM-based approaches."
}