We present our submission to the Task 5 of SemEval-2025 that aims to aid librarians in assigning subject tags to the library records by producing a list of likely relevant tags for a given document. 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. This approach proved effective, demonstrating significant improvements in recall compared to single-stage methods and showing competitive results according to qualitative evaluation.
View on arXiv@article{dorkin2025_2504.21547,
title={ TartuNLP at SemEval-2025 Task 5: Subject Tagging as Two-Stage Information Retrieval },
author={ Aleksei Dorkin and Kairit Sirts },
journal={arXiv preprint arXiv:2504.21547},
year={ 2025 }
}