ACL 2025long0 citations

ConLoan: A Contrastive Multilingual Dataset for Evaluating Loanwords

Sina Ahmadi, Micha David Hess, Elena Álvarez-Mellado, Alessia Battisti, Cui Ding, Anne Göhring, Yingqiang Gao, Zifan Jiang

Abstract

Lexical borrowing, the adoption of words from one language into another, is a ubiquitous linguistic phenomenon influenced by geopolitical, societal, and technological factors. This paper introduces ConLoan–a novel contrastive dataset comprising sentences with and without loanwords across 10 languages. Through systematic evaluation using this dataset, we investigate how state-of-the-art machine translation and language models process loanwords compared to their native alternatives. Our experiments reveal that these systems show systematic preferences for loanwords over native terms and exhibit varying performance across languages. These findings provide valuable insights for developing more linguistically robust NLP systems.

BibTeX
@inproceedings{ahmadi-etal-2025-conloan,
    title = "{C}on{L}oan: A Contrastive Multilingual Dataset for Evaluating Loanwords",
    author = {Ahmadi, Sina  and
      Hess, Micha David  and
      {\'A}lvarez-Mellado, Elena  and
      Battisti, Alessia  and
      Ding, Cui  and
      G{\"o}hring, Anne  and
      Gao, Yingqiang  and
      Jiang, Zifan  and
      Michail, Andrianos  and
      Morad, Peshmerge  and
      Niklaus, Joel  and
      Panagiotopoulou, Maria Christina  and
      Perrella, Stefano  and
      Opitz, Juri  and
      Shaitarova, Anastassia  and
      Sennrich, Rico},
    editor = "Che, Wanxiang  and
      Nabende, Joyce  and
      Shutova, Ekaterina  and
      Pilehvar, Mohammad Taher",
    booktitle = "Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
    month = jul,
    year = "2025",
    address = "Vienna, Austria",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2025.acl-long.1453/",
    doi = "10.18653/v1/2025.acl-long.1453",
    pages = "30070--30090",
    ISBN = "979-8-89176-251-0"
}
ConLoan: A Contrastive Multilingual Dataset for Evaluating Loanwords · ACL 2025