@inproceedings{michail-etal-2025-adapting,
    title = "Adapting Multilingual Embedding Models to Historical {L}uxembourgish",
    author = "Michail, Andrianos  and
      Racl{\'e}, Corina  and
      Opitz, Juri  and
      Clematide, Simon",
    editor = "Kazantseva, Anna  and
      Szpakowicz, Stan  and
      Degaetano-Ortlieb, Stefania  and
      Bizzoni, Yuri  and
      Pagel, Janis",
    booktitle = "Proceedings of the 9th Joint SIGHUM Workshop on Computational Linguistics for Cultural Heritage, Social Sciences, Humanities and Literature (LaTeCH-CLfL 2025)",
    month = may,
    year = "2025",
    address = "Albuquerque, New Mexico",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/moar-dois/2025.latechclfl-1.26/",
    doi = "10.18653/v1/2025.latechclfl-1.26",
    pages = "291--298",
    ISBN = "979-8-89176-241-1",
    abstract = "The growing volume of digitized historical texts requires effective semantic search using text embeddings. However, pre-trained multilingual models face challenges with historical content due to OCR noise and outdated spellings. This study examines multilingual embeddings for cross-lingual semantic search in historical Luxembourgish (LB), a low-resource language. We collect historical Luxembourgish news articles from various periods and use GPT-4o for sentence segmentation and translation, generating 20,000 parallel training sentences per language pair. Additionally, we create a semantic search (Historical LB Bitext Mining) evaluation set and find that existing models perform poorly on cross-lingual search for historical Luxembourgish. Using our historical and additional modern parallel training data, we adapt several multilingual embedding models through contrastive learning or knowledge distillation and increase accuracy significantly for all models. We release our adapted models and historical Luxembourgish-German/French/English bitexts to support further research."
}