JHU IWSLT 2025 Low-resource System Description

Nathaniel Romney Robinson; Niyati Bafna; Xiluo He; Tom Lupicki; Lavanya Shankar; Cihan Xiao; Qi Sun; Kenton Murray; David Yarowsky

doi:10.18653/v1/2025.iwslt-1.32

JHU IWSLT 2025 Low-resource System Description

Nathaniel Romney Robinson, Niyati Bafna, Xiluo He, Tom Lupicki, Lavanya Shankar, Cihan Xiao, Qi Sun, Kenton Murray, David Yarowsky

Correct Metadata for

Use this form to create a GitHub issue with structured data describing the correction. You will need a GitHub account. Once you create that issue, the correction will be reviewed by a staff member.

⚠️ Mobile Users: Submitting this form to create a new issue will only work with github.com, not the GitHub Mobile app.

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>. You may use <b>...</b> for bold, <i>...</i> for italic, and <url>...</url> for URLs.

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 the Johns Hopkins University’s submission to the 2025 IWSLT Low-Resource Task. We competed on all 10 language pairs. Our approach centers around ensembling methods – specifically Minimum Bayes Risk Decoding. We find that such ensembling often improves performance only slightly over the best performing stand-alone model, and that in some cases it can even hurt performance slightly.

Anthology ID:: 2025.iwslt-1.32
Volume:: Proceedings of the 22nd International Conference on Spoken Language Translation (IWSLT 2025)
Month:: July
Year:: 2025
Address:: Vienna, Austria (in-person and online)
Editors:: Elizabeth Salesky, Marcello Federico, Antonis Anastasopoulos
Venues:: IWSLT | WS
SIG:
Publisher:: Association for Computational Linguistics
Note:
Pages:: 315–323
Language:
URL:: https://aclanthology.org/2025.iwslt-1.32/
DOI:: 10.18653/v1/2025.iwslt-1.32
Bibkey:
Cite (ACL):: Nathaniel Romney Robinson, Niyati Bafna, Xiluo He, Tom Lupicki, Lavanya Shankar, Cihan Xiao, Qi Sun, Kenton Murray, and David Yarowsky. 2025. JHU IWSLT 2025 Low-resource System Description. In Proceedings of the 22nd International Conference on Spoken Language Translation (IWSLT 2025), pages 315–323, Vienna, Austria (in-person and online). Association for Computational Linguistics.
Cite (Informal):: JHU IWSLT 2025 Low-resource System Description (Romney Robinson et al., IWSLT 2025)
Copy Citation:
PDF:: https://aclanthology.org/2025.iwslt-1.32.pdf

PDF Cite Search Fix data

Export citation

BibTeX
MODS XML
Endnote
Preformatted

@inproceedings{romney-robinson-etal-2025-jhu,
    title = "{JHU} {IWSLT} 2025 Low-resource System Description",
    author = "Romney Robinson, Nathaniel  and
      Bafna, Niyati  and
      He, Xiluo  and
      Lupicki, Tom  and
      Shankar, Lavanya  and
      Xiao, Cihan  and
      Sun, Qi  and
      Murray, Kenton  and
      Yarowsky, David",
    editor = "Salesky, Elizabeth  and
      Federico, Marcello  and
      Anastasopoulos, Antonis",
    booktitle = "Proceedings of the 22nd International Conference on Spoken Language Translation (IWSLT 2025)",
    month = jul,
    year = "2025",
    address = "Vienna, Austria (in-person and online)",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2025.iwslt-1.32/",
    doi = "10.18653/v1/2025.iwslt-1.32",
    pages = "315--323",
    ISBN = "979-8-89176-272-5",
    abstract = "We present the Johns Hopkins University{'}s submission to the 2025 IWSLT Low-Resource Task. We competed on all 10 language pairs. Our approach centers around ensembling methods {--} specifically Minimum Bayes Risk Decoding. We find that such ensembling often improves performance only slightly over the best performing stand-alone model, and that in some cases it can even hurt performance slightly."
}

Download as File

<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="romney-robinson-etal-2025-jhu">
    <titleInfo>
        <title>JHU IWSLT 2025 Low-resource System Description</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Nathaniel</namePart>
        <namePart type="family">Romney Robinson</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Niyati</namePart>
        <namePart type="family">Bafna</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Xiluo</namePart>
        <namePart type="family">He</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Tom</namePart>
        <namePart type="family">Lupicki</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Lavanya</namePart>
        <namePart type="family">Shankar</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Cihan</namePart>
        <namePart type="family">Xiao</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Qi</namePart>
        <namePart type="family">Sun</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Kenton</namePart>
        <namePart type="family">Murray</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">David</namePart>
        <namePart type="family">Yarowsky</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 22nd International Conference on Spoken Language Translation (IWSLT 2025)</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Elizabeth</namePart>
            <namePart type="family">Salesky</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Marcello</namePart>
            <namePart type="family">Federico</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Antonis</namePart>
            <namePart type="family">Anastasopoulos</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Vienna, Austria (in-person and online)</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
        <identifier type="isbn">979-8-89176-272-5</identifier>
    </relatedItem>
    <abstract>We present the Johns Hopkins University’s submission to the 2025 IWSLT Low-Resource Task. We competed on all 10 language pairs. Our approach centers around ensembling methods – specifically Minimum Bayes Risk Decoding. We find that such ensembling often improves performance only slightly over the best performing stand-alone model, and that in some cases it can even hurt performance slightly.</abstract>
    <identifier type="citekey">romney-robinson-etal-2025-jhu</identifier>
    <identifier type="doi">10.18653/v1/2025.iwslt-1.32</identifier>
    <location>
        <url>https://aclanthology.org/2025.iwslt-1.32/</url>
    </location>
    <part>
        <date>2025-07</date>
        <extent unit="page">
            <start>315</start>
            <end>323</end>
        </extent>
    </part>
</mods>
</modsCollection>

Download as File

%0 Conference Proceedings
%T JHU IWSLT 2025 Low-resource System Description
%A Romney Robinson, Nathaniel
%A Bafna, Niyati
%A He, Xiluo
%A Lupicki, Tom
%A Shankar, Lavanya
%A Xiao, Cihan
%A Sun, Qi
%A Murray, Kenton
%A Yarowsky, David
%Y Salesky, Elizabeth
%Y Federico, Marcello
%Y Anastasopoulos, Antonis
%S Proceedings of the 22nd International Conference on Spoken Language Translation (IWSLT 2025)
%D 2025
%8 July
%I Association for Computational Linguistics
%C Vienna, Austria (in-person and online)
%@ 979-8-89176-272-5
%F romney-robinson-etal-2025-jhu
%X We present the Johns Hopkins University’s submission to the 2025 IWSLT Low-Resource Task. We competed on all 10 language pairs. Our approach centers around ensembling methods – specifically Minimum Bayes Risk Decoding. We find that such ensembling often improves performance only slightly over the best performing stand-alone model, and that in some cases it can even hurt performance slightly.
%R 10.18653/v1/2025.iwslt-1.32
%U https://aclanthology.org/2025.iwslt-1.32/
%U https://doi.org/10.18653/v1/2025.iwslt-1.32
%P 315-323

Download as File

Markdown (Informal)

[JHU IWSLT 2025 Low-resource System Description](https://aclanthology.org/2025.iwslt-1.32/) (Romney Robinson et al., IWSLT 2025)

JHU IWSLT 2025 Low-resource System Description (Romney Robinson et al., IWSLT 2025)

ACL

Nathaniel Romney Robinson, Niyati Bafna, Xiluo He, Tom Lupicki, Lavanya Shankar, Cihan Xiao, Qi Sun, Kenton Murray, and David Yarowsky. 2025. JHU IWSLT 2025 Low-resource System Description. In Proceedings of the 22nd International Conference on Spoken Language Translation (IWSLT 2025), pages 315–323, Vienna, Austria (in-person and online). Association for Computational Linguistics.