TartuNLP at SemEval-2025 Task 5: Subject Tagging as Two-Stage Information Retrieval
Not on the map. Why?
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.
Key facts. Cited by 1 paper 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
10 of 12 references.
References · 10
- 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,170
- 2020Dense Passage Retrieval for Open-Domain Question Answeringcited by 3,824
- 2021DeBERTaV3: Improving DeBERTa using ELECTRA-Style Pre-Training with Gradient-Disentangled Embedding Sharingcited by 1,254
- 2021BEIR: A Heterogenous Benchmark for Zero-shot Evaluation of Information Retrieval Modelscited by 1,252
- 2019Passage Re-ranking with BERTcited by 645
- 2025SemEval-2025 Task 5: LLMs4Subjects -- LLM-based Automated Subject Tagging for a National Technical Library's Open-Access Catalogcited by 10
- 2024Shallow Cross-Encoders for Low-Latency Retrievalcited by 4
- 2022Kratt: Developing an Automatic Subject Indexing Tool for The National Library of Estoniacited by 2
- 2024S~onajaht: Definition Embeddings and Semantic Search for Reverse Dictionary Creationcited by 2
- 2024TartuNLP @ AXOLOTL-24: Leveraging Classifier Output for New Sense Detection in Lexical Semanticscited by 1
Built on by
Citing papers per year: 2026: 1.
1 paper.