SYSTRAN @ WMT 2025 General Translation Task

Dakun Zhang; Yara Khater; Ramzi Rahli; Anna Rebollo; Josep M. Crego

SYSTRAN @ WMT 2025 General Translation Task

Dakun Zhang, Yara Khater, Ramzi Rahli, Anna Rebollo, Josep Crego

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 an English-to-Japanese translationsystem built upon the EuroLLM-9B (Martinset al., 2025) model. The training process involvestwo main stages: continue pretraining(CPT) and supervised fine-tuning (SFT). Afterboth stages, we further tuned the model using adevelopment set to optimize performance. Fortraining data, we employed both basic filteringtechniques and high-quality filtering strategiesto ensure data cleanness. Additionally, we classifyboth the training data and development datainto four different domains and we train andfine-tune with domain specific prompts duringsystem training. Finally, we applied MinimumBayes Risk (MBR) decoding and paragraph-levelreranking for post-processing to enhancetranslation quality.

Anthology ID:: 2025.wmt-1.35
Volume:: Proceedings of the Tenth Conference on Machine Translation
Month:: November
Year:: 2025
Address:: Suzhou, China
Editors:: Barry Haddow, Tom Kocmi, Philipp Koehn, Christof Monz
Venue:: WMT
SIG:
Publisher:: Association for Computational Linguistics
Note:
Pages:: 599–606
Language:
URL:: https://aclanthology.org/2025.wmt-1.35/
DOI:
Bibkey:
Cite (ACL):: Dakun Zhang, Yara Khater, Ramzi Rahli, Anna Rebollo, and Josep Crego. 2025. SYSTRAN @ WMT 2025 General Translation Task. In Proceedings of the Tenth Conference on Machine Translation, pages 599–606, Suzhou, China. Association for Computational Linguistics.
Cite (Informal):: SYSTRAN @ WMT 2025 General Translation Task (Zhang et al., WMT 2025)
Copy Citation:
PDF:: https://aclanthology.org/2025.wmt-1.35.pdf

PDF Cite Search Fix data

Export citation

BibTeX
MODS XML
Endnote
Preformatted

@inproceedings{zhang-etal-2025-systran,
    title = "{SYSTRAN} @ {WMT} 2025 General Translation Task",
    author = "Zhang, Dakun  and
      Khater, Yara  and
      Rahli, Ramzi  and
      Rebollo, Anna  and
      Crego, Josep",
    editor = "Haddow, Barry  and
      Kocmi, Tom  and
      Koehn, Philipp  and
      Monz, Christof",
    booktitle = "Proceedings of the Tenth Conference on Machine Translation",
    month = nov,
    year = "2025",
    address = "Suzhou, China",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2025.wmt-1.35/",
    pages = "599--606",
    ISBN = "979-8-89176-341-8",
    abstract = "We present an English-to-Japanese translationsystem built upon the EuroLLM-9B (Martinset al., 2025) model. The training process involvestwo main stages: continue pretraining(CPT) and supervised fine-tuning (SFT). Afterboth stages, we further tuned the model using adevelopment set to optimize performance. Fortraining data, we employed both basic filteringtechniques and high-quality filtering strategiesto ensure data cleanness. Additionally, we classifyboth the training data and development datainto four different domains and we train andfine-tune with domain specific prompts duringsystem training. Finally, we applied MinimumBayes Risk (MBR) decoding and paragraph-levelreranking for post-processing to enhancetranslation quality."
}

Download as File

<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhang-etal-2025-systran">
    <titleInfo>
        <title>SYSTRAN @ WMT 2025 General Translation Task</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Dakun</namePart>
        <namePart type="family">Zhang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Yara</namePart>
        <namePart type="family">Khater</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Ramzi</namePart>
        <namePart type="family">Rahli</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Anna</namePart>
        <namePart type="family">Rebollo</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Josep</namePart>
        <namePart type="family">Crego</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2025-11</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the Tenth Conference on Machine Translation</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Barry</namePart>
            <namePart type="family">Haddow</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Tom</namePart>
            <namePart type="family">Kocmi</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Philipp</namePart>
            <namePart type="family">Koehn</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Christof</namePart>
            <namePart type="family">Monz</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Suzhou, China</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
        <identifier type="isbn">979-8-89176-341-8</identifier>
    </relatedItem>
    <abstract>We present an English-to-Japanese translationsystem built upon the EuroLLM-9B (Martinset al., 2025) model. The training process involvestwo main stages: continue pretraining(CPT) and supervised fine-tuning (SFT). Afterboth stages, we further tuned the model using adevelopment set to optimize performance. Fortraining data, we employed both basic filteringtechniques and high-quality filtering strategiesto ensure data cleanness. Additionally, we classifyboth the training data and development datainto four different domains and we train andfine-tune with domain specific prompts duringsystem training. Finally, we applied MinimumBayes Risk (MBR) decoding and paragraph-levelreranking for post-processing to enhancetranslation quality.</abstract>
    <identifier type="citekey">zhang-etal-2025-systran</identifier>
    <location>
        <url>https://aclanthology.org/2025.wmt-1.35/</url>
    </location>
    <part>
        <date>2025-11</date>
        <extent unit="page">
            <start>599</start>
            <end>606</end>
        </extent>
    </part>
</mods>
</modsCollection>

Download as File

%0 Conference Proceedings
%T SYSTRAN @ WMT 2025 General Translation Task
%A Zhang, Dakun
%A Khater, Yara
%A Rahli, Ramzi
%A Rebollo, Anna
%A Crego, Josep
%Y Haddow, Barry
%Y Kocmi, Tom
%Y Koehn, Philipp
%Y Monz, Christof
%S Proceedings of the Tenth Conference on Machine Translation
%D 2025
%8 November
%I Association for Computational Linguistics
%C Suzhou, China
%@ 979-8-89176-341-8
%F zhang-etal-2025-systran
%X We present an English-to-Japanese translationsystem built upon the EuroLLM-9B (Martinset al., 2025) model. The training process involvestwo main stages: continue pretraining(CPT) and supervised fine-tuning (SFT). Afterboth stages, we further tuned the model using adevelopment set to optimize performance. Fortraining data, we employed both basic filteringtechniques and high-quality filtering strategiesto ensure data cleanness. Additionally, we classifyboth the training data and development datainto four different domains and we train andfine-tune with domain specific prompts duringsystem training. Finally, we applied MinimumBayes Risk (MBR) decoding and paragraph-levelreranking for post-processing to enhancetranslation quality.
%U https://aclanthology.org/2025.wmt-1.35/
%P 599-606

Download as File

Markdown (Informal)

[SYSTRAN @ WMT 2025 General Translation Task](https://aclanthology.org/2025.wmt-1.35/) (Zhang et al., WMT 2025)

SYSTRAN @ WMT 2025 General Translation Task (Zhang et al., WMT 2025)

ACL

Dakun Zhang, Yara Khater, Ramzi Rahli, Anna Rebollo, and Josep Crego. 2025. SYSTRAN @ WMT 2025 General Translation Task. In Proceedings of the Tenth Conference on Machine Translation, pages 599–606, Suzhou, China. Association for Computational Linguistics.