<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="song-2025-system">
    <titleInfo>
        <title>System Report for CCL25-Eval Task 12: Surpassing LLMs with a Simple Pipeline for Mandarin Spoken Entity-Relation Extraction</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Wuganjing</namePart>
        <namePart type="family">Song</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2025-08</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 24th China National Conference on Computational Linguistics (CCL 2025)</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Hongfei</namePart>
            <namePart type="family">Lin</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Bin</namePart>
            <namePart type="family">Li</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Hongye</namePart>
            <namePart type="family">Tan</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Chinese Information Processing Society of China</publisher>
            <place>
                <placeTerm type="text">Jinan, China</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>“We present a strong and practical pipeline system for Mandarin spoken entity and relation extraction (Spoken-ERE), which integrates an industrial-grade ASR module (FireRedASR) with a span-based joint entity-relation extraction model. Unlike recent approaches that rely on large language models (LLMs) for end-to-end spoken information extraction, our method uses a modular pipeline design that is lightweight, interpretable, and easy to deploy. Despite its simplicity,our system achieves top-tier performance in a recent shared task workshop, outperform-ing several 5× larger LLM-based systems for 20% on F1-score. We demonstrate through experiments that with robust ASR and a well-designed span-based model, classical pipelines re-main competitive and, in some scenarios, even preferable to LLM-based solutions for spoken information extraction in Mandarin.”</abstract>
    <identifier type="citekey">song-2025-system</identifier>
    <location>
        <url>https://aclanthology.org/2025.ccl-2.56/</url>
    </location>
    <part>
        <date>2025-08</date>
        <extent unit="page">
            <start>466</start>
            <end>469</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T System Report for CCL25-Eval Task 12: Surpassing LLMs with a Simple Pipeline for Mandarin Spoken Entity-Relation Extraction
%A Song, Wuganjing
%Y Lin, Hongfei
%Y Li, Bin
%Y Tan, Hongye
%S Proceedings of the 24th China National Conference on Computational Linguistics (CCL 2025)
%D 2025
%8 August
%I Chinese Information Processing Society of China
%C Jinan, China
%F song-2025-system
%X “We present a strong and practical pipeline system for Mandarin spoken entity and relation extraction (Spoken-ERE), which integrates an industrial-grade ASR module (FireRedASR) with a span-based joint entity-relation extraction model. Unlike recent approaches that rely on large language models (LLMs) for end-to-end spoken information extraction, our method uses a modular pipeline design that is lightweight, interpretable, and easy to deploy. Despite its simplicity,our system achieves top-tier performance in a recent shared task workshop, outperform-ing several 5× larger LLM-based systems for 20% on F1-score. We demonstrate through experiments that with robust ASR and a well-designed span-based model, classical pipelines re-main competitive and, in some scenarios, even preferable to LLM-based solutions for spoken information extraction in Mandarin.”
%U https://aclanthology.org/2025.ccl-2.56/
%P 466-469

Markdown (Informal)

[System Report for CCL25-Eval Task 12: Surpassing LLMs with a Simple Pipeline for Mandarin Spoken Entity-Relation Extraction](https://aclanthology.org/2025.ccl-2.56/) (Song, CCL 2025)

• System Report for CCL25-Eval Task 12: Surpassing LLMs with a Simple Pipeline for Mandarin Spoken Entity-Relation Extraction (Song, CCL 2025)

ACL

• Wuganjing Song. 2025. System Report for CCL25-Eval Task 12: Surpassing LLMs with a Simple Pipeline for Mandarin Spoken Entity-Relation Extraction. In Proceedings of the 24th China National Conference on Computational Linguistics (CCL 2025), pages 466–469, Jinan, China. Chinese Information Processing Society of China.