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

arXiv: https://arxiv.org/abs/2504.21547 · HTML: https://mlsanity.com/paper/2504.21547/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 10 of its 12 references that are in the map.
- First posted on arXiv 30 Apr 2025.

## Builds on (most cited first, 10 of 10)

- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [Dense Passage Retrieval for Open-Domain Question Answering](https://mlsanity.com/paper/2004.04906/) (2020)
- [DeBERTaV3: Improving DeBERTa using ELECTRA-Style Pre-Training with Gradient-Disentangled Embedding Sharing](https://mlsanity.com/paper/2111.09543/) (2021)
- [BEIR: A Heterogenous Benchmark for Zero-shot Evaluation of Information Retrieval Models](https://mlsanity.com/paper/2104.08663/) (2021)
- [Passage Re-ranking with BERT](https://mlsanity.com/paper/1901.04085/) (2019)
- [SemEval-2025 Task 5: LLMs4Subjects -- LLM-based Automated Subject Tagging for a National Technical Library's Open-Access Catalog](https://mlsanity.com/paper/2504.07199/) (2025)
- [Shallow Cross-Encoders for Low-Latency Retrieval](https://mlsanity.com/paper/2403.20222/) (2024)
- [Kratt: Developing an Automatic Subject Indexing Tool for The National Library of Estonia](https://mlsanity.com/paper/2203.12998/) (2022)
- [S~onajaht: Definition Embeddings and Semantic Search for Reverse Dictionary Creation](https://mlsanity.com/paper/2404.19430/) (2024)
- [TartuNLP @ AXOLOTL-24: Leveraging Classifier Output for New Sense Detection in Lexical Semantics](https://mlsanity.com/paper/2407.03861/) (2024)

## Built on by (most cited first, 1 of 1)

- [An Extreme Multi-label Text Classification (XMTC) Library Dataset: What if we took "Use of Practical AI in Digital Libraries" seriously?](https://mlsanity.com/paper/2603.10876/) (2026)

## Abstract (arXiv)

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.