TartuNLP at SemEval-2025 Task 5: Subject Tagging as Two-Stage Information Retrieval

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Dorkin, Aleksei, Sirts, Kairit
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912354835365888
author Dorkin, Aleksei
Sirts, Kairit
author_facet Dorkin, Aleksei
Sirts, Kairit
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2504_21547
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle TartuNLP at SemEval-2025 Task 5: Subject Tagging as Two-Stage Information Retrieval
Dorkin, Aleksei
Sirts, Kairit
Computation and Language
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.
title TartuNLP at SemEval-2025 Task 5: Subject Tagging as Two-Stage Information Retrieval
topic Computation and Language
url https://arxiv.org/abs/2504.21547