@inproceedings{zeidler-etal-2025-spanish,
    title = "{S}panish Dialect Classification: A Comparative Study of Linguistically Tailored Features, Unigrams and {BERT} Embeddings",
    author = "Zeidler, Laura  and
      Jenkins, Chris  and
      Mileti{\'c}, Filip  and
      Schulte Im Walde, Sabine",
    editor = "Zhao, Jin  and
      Wang, Mingyang  and
      Liu, Zhu",
    booktitle = "Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 4: Student Research Workshop)",
    month = jul,
    year = "2025",
    address = "Vienna, Austria",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingestion-acl-25/2025.acl-srw.36/",
    pages = "539--547",
    ISBN = "979-8-89176-254-1",
    abstract = "The task of automatic dialect classification is typically tackled using traditional machine-learning models with bag-of-words unigram features. We explore two alternative methods for distinguishing dialects across 20 Spanish-speaking countries:(i) Support vector machine and decision tree models were trained on dialectal features tailored to the Spanish dialects, combined with standard unigrams. (ii) A pre-trained BERT model was fine-tuned on the task.Results show that the tailored features generally did not have a positive impact on traditional model performance, but provide a salient way of representing dialects in a content-agnostic manner. The BERT model wins over traditional models but with only a tiny margin, while sacrificing explainability and interpretability."
}