<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="chen-2025-pingan">
    <titleInfo>
        <title>pingan-team at SemEval-2025 Task 2: LoRA-Augmented Qwen2.5 with Wikidata-Driven Entity Translation</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Diyang</namePart>
        <namePart type="family">Chen</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 presents our solution for SemEval-2025 Task 2 on entity-aware machine translation. We propose a parameter-efficient adaptation framework using Low-Rank Adaptation (LoRA) to fine-tune the Qwen2.5-72B model, enabling effective knowledge transfer while preserving generalization capabilities. To address data scarcity and entity ambiguity, we design a Wiki-driven augmentation pipeline that leverages Wikidata’s multilingual entity mappings to generate synthetic training pairs. Our system achieves state-of-the-art performance across 10 languages, securing first place in the competition. Experimental results demonstrate significant improvements in both translation quality (COMET) and entity accuracy (M-ETA).</abstract>
    <identifier type="citekey">chen-2025-pingan</identifier>
    <location>
        <url>https://aclanthology.org/2025.semeval-1.268/</url>
    </location>
    <part>
        <date>2025-07</date>
        <extent unit="page">
            <start>2065</start>
            <end>2070</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T pingan-team at SemEval-2025 Task 2: LoRA-Augmented Qwen2.5 with Wikidata-Driven Entity Translation
%A Chen, Diyang
%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 chen-2025-pingan
%X This paper presents our solution for SemEval-2025 Task 2 on entity-aware machine translation. We propose a parameter-efficient adaptation framework using Low-Rank Adaptation (LoRA) to fine-tune the Qwen2.5-72B model, enabling effective knowledge transfer while preserving generalization capabilities. To address data scarcity and entity ambiguity, we design a Wiki-driven augmentation pipeline that leverages Wikidata’s multilingual entity mappings to generate synthetic training pairs. Our system achieves state-of-the-art performance across 10 languages, securing first place in the competition. Experimental results demonstrate significant improvements in both translation quality (COMET) and entity accuracy (M-ETA).
%U https://aclanthology.org/2025.semeval-1.268/
%P 2065-2070

Markdown (Informal)

[pingan-team at SemEval-2025 Task 2: LoRA-Augmented Qwen2.5 with Wikidata-Driven Entity Translation](https://aclanthology.org/2025.semeval-1.268/) (Chen, SemEval 2025)

• pingan-team at SemEval-2025 Task 2: LoRA-Augmented Qwen2.5 with Wikidata-Driven Entity Translation (Chen, SemEval 2025)

ACL

• Diyang Chen. 2025. pingan-team at SemEval-2025 Task 2: LoRA-Augmented Qwen2.5 with Wikidata-Driven Entity Translation. In Proceedings of the 19th International Workshop on Semantic Evaluation (SemEval-2025), pages 2065–2070, Vienna, Austria. Association for Computational Linguistics.