@inproceedings{noviello-tamburini-2024-exploring,
    title = "Exploring Text-Embedding Retrieval Models for the {I}talian Language",
    author = "Noviello, Yuri  and
      Tamburini, Fabio",
    editor = "Dell'Orletta, Felice  and
      Lenci, Alessandro  and
      Montemagni, Simonetta  and
      Sprugnoli, Rachele",
    booktitle = "Proceedings of the 10th Italian Conference on Computational Linguistics (CLiC-it 2024)",
    month = dec,
    year = "2024",
    address = "Pisa, Italy",
    publisher = "CEUR Workshop Proceedings",
    url = "https://preview.aclanthology.org/jlcl-multiple-ingestion/2024.clicit-1.73/",
    pages = "654--661",
    ISBN = "979-12-210-7060-6",
    abstract = "Text retrieval systems have become essential in the field of natural language processing (NLP), serving as the backbone for applications such as search engines, document indexing, and information retrieval. With the rise of generative AI, particularly Retrieval-Augmented Generation (RAG) systems, the demand for robust text retrieval models has increased. However, existing large language models (LLMs) and datasets are often insufficiently optimized for Italian, limiting their performance in Italian text retrieval tasks. This paper addresses this gap by proposing both a data collection and specialized models tailored for Italian text retrieval. Through extensive experimentation, we analyze the improvements and limitations in retrieval performance, paving the way for more effective Italian NLP applications."
}