@inproceedings{gonzalez-gutierrez-quattoni-2025-domain,
    title = "Domain Pre-training Impact on Representations",
    author = "Gonzalez-Gutierrez, Cesar  and
      Quattoni, Ariadna",
    editor = "Christodoulopoulos, Christos  and
      Chakraborty, Tanmoy  and
      Rose, Carolyn  and
      Peng, Violet",
    booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2025",
    month = nov,
    year = "2025",
    address = "Suzhou, China",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/author-page-yu-wang-polytechnic/2025.findings-emnlp.1201/",
    doi = "10.18653/v1/2025.findings-emnlp.1201",
    pages = "22033--22049",
    ISBN = "979-8-89176-335-7",
    abstract = "This empirical study analyzes how the choice of pre-training corpus affects the quality of learned transformer representations. We focus specifically on the representation quality achieved through pre-training alone. Our experiments demonstrate that pre-training on a small, specialized corpus can produce effective representations, and that the effectiveness of combining a generic and a specialized corpora depends on the distributional similarity between the target task and the specialized corpus."
}