@inproceedings{xu-2025-wikidata,
    title = "{W}ikidata-Driven Entity-Aware Translation: Boosting {LLM}s with External Knowledge",
    author = "Xu, Lu",
    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/corrections-2025-08/2025.semeval-1.238/",
    pages = "1802--1809",
    ISBN = "979-8-89176-273-2",
    abstract = "This paper presents an entity-aware machine translation system that significantly improves named entity translation by integrating external knowledge from Wikidata with Large Language Models (LLMs). While LLMs demonstrate strong general translation capabilities, they struggle with named entities that require specific cultural or domain knowledge. We address this challenge through two approaches: retrieving multilingual entity representations using gold Wikidata IDs, and employing Relik, an information extraction tool, to automatically detect and link entities without gold annotations. Experiments across multiple language pairs show our system outperforms baselines by up to 63 percentage points in entity translation accuracy (m-ETA) while maintaining high overall translation quality. Our approach ranked 3rd overall and 1st among non-finetuned systems on the SemEval-2025 Task 2 leaderboard. Additionally, we introduced language-specific post-processing further enhances performance, particularly for Traditional Chinese translations."
}