@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://aclanthology.org/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."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="dorkin-sirts-2025-tartunlp">
<titleInfo>
<title>TartuNLP at SemEval-2025 Task 5: Subject Tagging as Two-Stage Information Retrieval</title>
</titleInfo>
<name type="personal">
<namePart type="given">Aleksei</namePart>
<namePart type="family">Dorkin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kairit</namePart>
<namePart type="family">Sirts</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 19th International Workshop on Semantic Evaluation (SemEval-2025)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sara</namePart>
<namePart type="family">Rosenthal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aiala</namePart>
<namePart type="family">Rosá</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Debanjan</namePart>
<namePart type="family">Ghosh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marcos</namePart>
<namePart type="family">Zampieri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Vienna, Austria</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-273-2</identifier>
</relatedItem>
<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.</abstract>
<identifier type="citekey">dorkin-sirts-2025-tartunlp</identifier>
<location>
<url>https://aclanthology.org/2025.semeval-1.319/</url>
</location>
<part>
<date>2025-07</date>
<extent unit="page">
<start>2449</start>
<end>2454</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T TartuNLP at SemEval-2025 Task 5: Subject Tagging as Two-Stage Information Retrieval
%A Dorkin, Aleksei
%A Sirts, Kairit
%Y Rosenthal, Sara
%Y Rosá, Aiala
%Y Ghosh, Debanjan
%Y Zampieri, Marcos
%S Proceedings of the 19th International Workshop on Semantic Evaluation (SemEval-2025)
%D 2025
%8 July
%I Association for Computational Linguistics
%C Vienna, Austria
%@ 979-8-89176-273-2
%F dorkin-sirts-2025-tartunlp
%X 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.
%U https://aclanthology.org/2025.semeval-1.319/
%P 2449-2454
Markdown (Informal)
[TartuNLP at SemEval-2025 Task 5: Subject Tagging as Two-Stage Information Retrieval](https://aclanthology.org/2025.semeval-1.319/) (Dorkin & Sirts, SemEval 2025)
ACL