@inproceedings{jiang-etal-2025-ynu,
title = "{YNU}-{HPCC} at {S}em{E}val-2025 Task 5: Contrastive Learning for {GND} Subject Tagging with Multilingual Sentence-{BERT}",
author = "Jiang, Hong and
Wang, Jin and
Zhang, Xuejie",
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-1.318/",
pages = "2443--2448",
ISBN = "979-8-89176-273-2",
abstract = "This paper describes YNU-HPCC(Alias JH) team{'}s participation in the sub-task 2 of the SemEval-2025 Task 5, which requires fine-tuning language models to align subject tags with the TIBKAT collection. The task presents three key challenges: cross-disciplinary document coverage, bilingual (English-German) processing requirements, and extreme classification over 200,000 GND Subjects. To address these challenges, we apply a contrastive learning framework using multilingual Sentence-BERT models, implementing two innovative training strategies: mixed-negative multi-label sampling, and single-label sampling with random negative selection. Our best-performing model achieves significant improvements of 28.6{\%} in average recall, reaching 0.2252 on the core-test set and 0.1677 on the all-test set. Notably, we reveal model architecture-dependent response patterns: MiniLM-series models benefit from multi-label training (+33.5{\%} zero-shot recall), while mpnet variants excel with single-label approaches (+230.3{\%} zero-shot recall). The study further demonstrates the effectiveness of contrastive learning for multilingual semantic alignment in low-resource scenarios, providing insights for extreme classification tasks."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="jiang-etal-2025-ynu">
<titleInfo>
<title>YNU-HPCC at SemEval-2025 Task 5: Contrastive Learning for GND Subject Tagging with Multilingual Sentence-BERT</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hong</namePart>
<namePart type="family">Jiang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jin</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xuejie</namePart>
<namePart type="family">Zhang</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>This paper describes YNU-HPCC(Alias JH) team’s participation in the sub-task 2 of the SemEval-2025 Task 5, which requires fine-tuning language models to align subject tags with the TIBKAT collection. The task presents three key challenges: cross-disciplinary document coverage, bilingual (English-German) processing requirements, and extreme classification over 200,000 GND Subjects. To address these challenges, we apply a contrastive learning framework using multilingual Sentence-BERT models, implementing two innovative training strategies: mixed-negative multi-label sampling, and single-label sampling with random negative selection. Our best-performing model achieves significant improvements of 28.6% in average recall, reaching 0.2252 on the core-test set and 0.1677 on the all-test set. Notably, we reveal model architecture-dependent response patterns: MiniLM-series models benefit from multi-label training (+33.5% zero-shot recall), while mpnet variants excel with single-label approaches (+230.3% zero-shot recall). The study further demonstrates the effectiveness of contrastive learning for multilingual semantic alignment in low-resource scenarios, providing insights for extreme classification tasks.</abstract>
<identifier type="citekey">jiang-etal-2025-ynu</identifier>
<location>
<url>https://aclanthology.org/2025.semeval-1.318/</url>
</location>
<part>
<date>2025-07</date>
<extent unit="page">
<start>2443</start>
<end>2448</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T YNU-HPCC at SemEval-2025 Task 5: Contrastive Learning for GND Subject Tagging with Multilingual Sentence-BERT
%A Jiang, Hong
%A Wang, Jin
%A Zhang, Xuejie
%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 jiang-etal-2025-ynu
%X This paper describes YNU-HPCC(Alias JH) team’s participation in the sub-task 2 of the SemEval-2025 Task 5, which requires fine-tuning language models to align subject tags with the TIBKAT collection. The task presents three key challenges: cross-disciplinary document coverage, bilingual (English-German) processing requirements, and extreme classification over 200,000 GND Subjects. To address these challenges, we apply a contrastive learning framework using multilingual Sentence-BERT models, implementing two innovative training strategies: mixed-negative multi-label sampling, and single-label sampling with random negative selection. Our best-performing model achieves significant improvements of 28.6% in average recall, reaching 0.2252 on the core-test set and 0.1677 on the all-test set. Notably, we reveal model architecture-dependent response patterns: MiniLM-series models benefit from multi-label training (+33.5% zero-shot recall), while mpnet variants excel with single-label approaches (+230.3% zero-shot recall). The study further demonstrates the effectiveness of contrastive learning for multilingual semantic alignment in low-resource scenarios, providing insights for extreme classification tasks.
%U https://aclanthology.org/2025.semeval-1.318/
%P 2443-2448
Markdown (Informal)
[YNU-HPCC at SemEval-2025 Task 5: Contrastive Learning for GND Subject Tagging with Multilingual Sentence-BERT](https://aclanthology.org/2025.semeval-1.318/) (Jiang et al., SemEval 2025)
ACL