@inproceedings{dorkin-sirts-2025-tartunlp,
    title = "{T}artu{NLP} at {S}em{E}val-2025 Task 5: Subject Tagging as Two-Stage Information Retrieval",
    author = "Dorkin, Aleksei  and
      Sirts, Kairit",
    editor = "Rosenthal, Sara  and
      Ros{\'a}, Aiala  and
      Ghosh, Debanjan  and
      Zampieri, Marcos",
    booktitle = "Proceedings of the 19th International Workshop on Semantic Evaluation (SemEval-2025)",
    month = jul,
    year = "2025",
    address = "Vienna, Austria",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/corrections-2025-08/2025.semeval-1.319/",
    pages = "2449--2454",
    ISBN = "979-8-89176-273-2",
    abstract = "We present our submission to the Task 5 of SemEval-2025. We frame the task as an information retrieval problem, where the document content is used to retrieve subject tags from a large subject taxonomy. We leverage two types of encoder models to build a two-stage information retrieval system{---}a bi-encoder for coarse-grained candidate extraction at the first stage, and a cross-encoder for fine-grained re-ranking at the second stage."
}