DeRAGEC: Denoising Named Entity Candidates with Synthetic Rationale for ASR Error Correction

Solee Im; Wonjun Lee; Jinmyeong An; Yunsu Kim; Jungseul Ok; Gary Lee

doi:10.18653/v1/2025.findings-acl.786

DeRAGEC: Denoising Named Entity Candidates with Synthetic Rationale for ASR Error Correction

Solee Im, Wonjun Lee, JinMyeong An, Yunsu Kim, Jungseul Ok, Gary Lee

Correct Metadata for

Important: The Anthology treat PDFs as authoritative. Please use this form only to correct data that is out of line with the PDF. See our corrections guidelines if you need to change the PDF.

Title Adjust the title. Retain tags such as <fixed-case>.

Authors Adjust author names and order to match the PDF.

Abstract Correct abstract if needed. Retain XML formatting tags such as <tex-math>.

Verification against PDF Ensure that the new title/authors match the snapshot below. (If there is no snapshot or it is too small, consult the PDF.)

Authors concatenated from the text boxes above:

ALL author names match the snapshot above—including middle initials, hyphens, and accents.

Abstract

We present DeRAGEC, a method for improving Named Entity (NE) correction in Automatic Speech Recognition (ASR) systems. By extending the Retrieval-Augmented Generative Error Correction (RAGEC) framework, DeRAGEC employs synthetic denoising rationales to filter out noisy NE candidates before correction. By leveraging phonetic similarity and augmented definitions, it refines noisy retrieved NEs using in-context learning, requiring no additional training. Experimental results on CommonVoice and STOP datasets show significant improvements in Word Error Rate (WER) and NE hit ratio, outperforming baseline ASR and RAGEC methods. Specifically, we achieved a 28% relative reduction in WER compared to ASR without postprocessing.

Anthology ID:: 2025.findings-acl.786
Volume:: Findings of the Association for Computational Linguistics: ACL 2025
Month:: July
Year:: 2025
Address:: Vienna, Austria
Editors:: Wanxiang Che, Joyce Nabende, Ekaterina Shutova, Mohammad Taher Pilehvar
Venue:: Findings
SIG:
Publisher:: Association for Computational Linguistics
Note:
Pages:: 15181–15193
Language:
URL:: https://aclanthology.org/2025.findings-acl.786/
DOI:: 10.18653/v1/2025.findings-acl.786
Bibkey:
Cite (ACL):: Solee Im, Wonjun Lee, JinMyeong An, Yunsu Kim, Jungseul Ok, and Gary Lee. 2025. DeRAGEC: Denoising Named Entity Candidates with Synthetic Rationale for ASR Error Correction. In Findings of the Association for Computational Linguistics: ACL 2025, pages 15181–15193, Vienna, Austria. Association for Computational Linguistics.
Cite (Informal):: DeRAGEC: Denoising Named Entity Candidates with Synthetic Rationale for ASR Error Correction (Im et al., Findings 2025)
Copy Citation:
PDF:: https://aclanthology.org/2025.findings-acl.786.pdf

PDF Cite Search Fix data

Export citation

BibTeX
MODS XML
Endnote
Preformatted

@inproceedings{im-etal-2025-deragec,
    title = "{D}e{RAGEC}: Denoising Named Entity Candidates with Synthetic Rationale for {ASR} Error Correction",
    author = "Im, Solee  and
      Lee, Wonjun  and
      An, JinMyeong  and
      Kim, Yunsu  and
      Ok, Jungseul  and
      Lee, Gary",
    editor = "Che, Wanxiang  and
      Nabende, Joyce  and
      Shutova, Ekaterina  and
      Pilehvar, Mohammad Taher",
    booktitle = "Findings of the Association for Computational Linguistics: ACL 2025",
    month = jul,
    year = "2025",
    address = "Vienna, Austria",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2025.findings-acl.786/",
    doi = "10.18653/v1/2025.findings-acl.786",
    pages = "15181--15193",
    ISBN = "979-8-89176-256-5",
    abstract = "We present DeRAGEC, a method for improving Named Entity (NE) correction in Automatic Speech Recognition (ASR) systems. By extending the Retrieval-Augmented Generative Error Correction (RAGEC) framework, DeRAGEC employs synthetic denoising rationales to filter out noisy NE candidates before correction. By leveraging phonetic similarity and augmented definitions, it refines noisy retrieved NEs using in-context learning, requiring no additional training. Experimental results on CommonVoice and STOP datasets show significant improvements in Word Error Rate (WER) and NE hit ratio, outperforming baseline ASR and RAGEC methods. Specifically, we achieved a 28{\%} relative reduction in WER compared to ASR without postprocessing."
}

Download as File

<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="im-etal-2025-deragec">
    <titleInfo>
        <title>DeRAGEC: Denoising Named Entity Candidates with Synthetic Rationale for ASR Error Correction</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Solee</namePart>
        <namePart type="family">Im</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Wonjun</namePart>
        <namePart type="family">Lee</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">JinMyeong</namePart>
        <namePart type="family">An</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Yunsu</namePart>
        <namePart type="family">Kim</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Jungseul</namePart>
        <namePart type="family">Ok</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Gary</namePart>
        <namePart type="family">Lee</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>Findings of the Association for Computational Linguistics: ACL 2025</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Wanxiang</namePart>
            <namePart type="family">Che</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Joyce</namePart>
            <namePart type="family">Nabende</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Ekaterina</namePart>
            <namePart type="family">Shutova</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Mohammad</namePart>
            <namePart type="given">Taher</namePart>
            <namePart type="family">Pilehvar</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">979-8-89176-256-5</identifier>
    </relatedItem>
    <abstract>We present DeRAGEC, a method for improving Named Entity (NE) correction in Automatic Speech Recognition (ASR) systems. By extending the Retrieval-Augmented Generative Error Correction (RAGEC) framework, DeRAGEC employs synthetic denoising rationales to filter out noisy NE candidates before correction. By leveraging phonetic similarity and augmented definitions, it refines noisy retrieved NEs using in-context learning, requiring no additional training. Experimental results on CommonVoice and STOP datasets show significant improvements in Word Error Rate (WER) and NE hit ratio, outperforming baseline ASR and RAGEC methods. Specifically, we achieved a 28% relative reduction in WER compared to ASR without postprocessing.</abstract>
    <identifier type="citekey">im-etal-2025-deragec</identifier>
    <identifier type="doi">10.18653/v1/2025.findings-acl.786</identifier>
    <location>
        <url>https://aclanthology.org/2025.findings-acl.786/</url>
    </location>
    <part>
        <date>2025-07</date>
        <extent unit="page">
            <start>15181</start>
            <end>15193</end>
        </extent>
    </part>
</mods>
</modsCollection>

Download as File

%0 Conference Proceedings
%T DeRAGEC: Denoising Named Entity Candidates with Synthetic Rationale for ASR Error Correction
%A Im, Solee
%A Lee, Wonjun
%A An, JinMyeong
%A Kim, Yunsu
%A Ok, Jungseul
%A Lee, Gary
%Y Che, Wanxiang
%Y Nabende, Joyce
%Y Shutova, Ekaterina
%Y Pilehvar, Mohammad Taher
%S Findings of the Association for Computational Linguistics: ACL 2025
%D 2025
%8 July
%I Association for Computational Linguistics
%C Vienna, Austria
%@ 979-8-89176-256-5
%F im-etal-2025-deragec
%X We present DeRAGEC, a method for improving Named Entity (NE) correction in Automatic Speech Recognition (ASR) systems. By extending the Retrieval-Augmented Generative Error Correction (RAGEC) framework, DeRAGEC employs synthetic denoising rationales to filter out noisy NE candidates before correction. By leveraging phonetic similarity and augmented definitions, it refines noisy retrieved NEs using in-context learning, requiring no additional training. Experimental results on CommonVoice and STOP datasets show significant improvements in Word Error Rate (WER) and NE hit ratio, outperforming baseline ASR and RAGEC methods. Specifically, we achieved a 28% relative reduction in WER compared to ASR without postprocessing.
%R 10.18653/v1/2025.findings-acl.786
%U https://aclanthology.org/2025.findings-acl.786/
%U https://doi.org/10.18653/v1/2025.findings-acl.786
%P 15181-15193

Download as File

Markdown (Informal)

[DeRAGEC: Denoising Named Entity Candidates with Synthetic Rationale for ASR Error Correction](https://aclanthology.org/2025.findings-acl.786/) (Im et al., Findings 2025)

DeRAGEC: Denoising Named Entity Candidates with Synthetic Rationale for ASR Error Correction (Im et al., Findings 2025)

ACL

Solee Im, Wonjun Lee, JinMyeong An, Yunsu Kim, Jungseul Ok, and Gary Lee. 2025. DeRAGEC: Denoising Named Entity Candidates with Synthetic Rationale for ASR Error Correction. In Findings of the Association for Computational Linguistics: ACL 2025, pages 15181–15193, Vienna, Austria. Association for Computational Linguistics.