@inproceedings{lei-etal-2025-ynu,
title = "{YNU}-{HPCC} at {S}em{E}val-2025 Task 1: Enhancing Multimodal Idiomaticity Representation via {L}o{RA} and Hybrid Loss Optimization",
author = "Lei, Liu and
Zhang, You and
Wang, Jin and
Xu, Dan 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-1.270/",
pages = "2077--2083",
ISBN = "979-8-89176-273-2",
abstract = "This study reports the YNU-HPCC team{'}s participation in Subtask A of SemEval-2025 Task 1 on multimodal idiomatic representation. The task requires ranking candidate images based on their semantic relevance to a target idiom within a given sentence, challenging models to disambiguate idiomatic semantics, and aligning them with abstract visual concepts across English and Portuguese. Using AltCLIP-m18 as the base model, our approach enhances its zero-shot capabilities with LoRA fine-tuning and combines ListMLE ranking optimization with Focal Loss to handle hard samples. Experimental results on the primary test set show significant improvements over the base model, with Top-1 Accuracy/DCG scores of 0.53/2.94 for English and 0.77/3.31 for Portuguese. The code is publicly available at https://github.com/1579364808/Semeval{\_}2025{\_}task1."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="lei-etal-2025-ynu">
<titleInfo>
<title>YNU-HPCC at SemEval-2025 Task 1: Enhancing Multimodal Idiomaticity Representation via LoRA and Hybrid Loss Optimization</title>
</titleInfo>
<name type="personal">
<namePart type="given">Liu</namePart>
<namePart type="family">Lei</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">You</namePart>
<namePart type="family">Zhang</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">Dan</namePart>
<namePart type="family">Xu</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 study reports the YNU-HPCC team’s participation in Subtask A of SemEval-2025 Task 1 on multimodal idiomatic representation. The task requires ranking candidate images based on their semantic relevance to a target idiom within a given sentence, challenging models to disambiguate idiomatic semantics, and aligning them with abstract visual concepts across English and Portuguese. Using AltCLIP-m18 as the base model, our approach enhances its zero-shot capabilities with LoRA fine-tuning and combines ListMLE ranking optimization with Focal Loss to handle hard samples. Experimental results on the primary test set show significant improvements over the base model, with Top-1 Accuracy/DCG scores of 0.53/2.94 for English and 0.77/3.31 for Portuguese. The code is publicly available at https://github.com/1579364808/Semeval_2025_task1.</abstract>
<identifier type="citekey">lei-etal-2025-ynu</identifier>
<location>
<url>https://aclanthology.org/2025.semeval-1.270/</url>
</location>
<part>
<date>2025-07</date>
<extent unit="page">
<start>2077</start>
<end>2083</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T YNU-HPCC at SemEval-2025 Task 1: Enhancing Multimodal Idiomaticity Representation via LoRA and Hybrid Loss Optimization
%A Lei, Liu
%A Zhang, You
%A Wang, Jin
%A Xu, Dan
%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 lei-etal-2025-ynu
%X This study reports the YNU-HPCC team’s participation in Subtask A of SemEval-2025 Task 1 on multimodal idiomatic representation. The task requires ranking candidate images based on their semantic relevance to a target idiom within a given sentence, challenging models to disambiguate idiomatic semantics, and aligning them with abstract visual concepts across English and Portuguese. Using AltCLIP-m18 as the base model, our approach enhances its zero-shot capabilities with LoRA fine-tuning and combines ListMLE ranking optimization with Focal Loss to handle hard samples. Experimental results on the primary test set show significant improvements over the base model, with Top-1 Accuracy/DCG scores of 0.53/2.94 for English and 0.77/3.31 for Portuguese. The code is publicly available at https://github.com/1579364808/Semeval_2025_task1.
%U https://aclanthology.org/2025.semeval-1.270/
%P 2077-2083
Markdown (Informal)
[YNU-HPCC at SemEval-2025 Task 1: Enhancing Multimodal Idiomaticity Representation via LoRA and Hybrid Loss Optimization](https://aclanthology.org/2025.semeval-1.270/) (Lei et al., SemEval 2025)
ACL