<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="yan-hu-2026-direction">
    <titleInfo>
        <title>A Direction-Specialized System for WMT26 Chinese-Southeast Asian Multilingual Machine Translation</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Xiaojing</namePart>
        <namePart type="family">Yan</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Rile</namePart>
        <namePart type="family">Hu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2026-10</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the Eleventh 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">Budapest, Hungary</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
        <identifier type="isbn">979-8-89176-474-3</identifier>
    </relatedItem>
    <abstract>We describe a lightweight system for the WMT26 Chinese-Southeast Asian Multilingual Translation Task, covering 14 directions between Chinese and seven Southeast Asian languages. It uses two independently trained Transformer Base models: a one-to-many (OTM) model for translation from Chinese and a many-to-one (MTO) model for translation into Chinese. Each model has 68,727,808 unique parameters. Both use 134,645 real parallel sentence pairs, augmented with 154,452 back-translated pairs for OTM and a 96,000-pair subset with synthetic Chinese targets for MTO. On the 6,859-pair internal test set, the final CTranslate2-based system achieves direction-family macro-average BLEU scores of 43.70 and 49.03; on the FLORES-200 crossdomain test set, they are 17.52 and 26.03, respectively. A CT2-only microbenchmark on a single NVIDIA GeForce RTX 5090 achieves 237.02 and 241.96 sentences per second on presegmented, source-length-stratified development samples, using the median of three steadystate measurements.</abstract>
    <identifier type="citekey">yan-hu-2026-direction</identifier>
    <location>
        <url>https://aclanthology.org/2026.wmt-main.183/</url>
    </location>
    <part>
        <date>2026-10</date>
        <extent unit="page">
            <start>2389</start>
            <end>2396</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T A Direction-Specialized System for WMT26 Chinese-Southeast Asian Multilingual Machine Translation
%A Yan, Xiaojing
%A Hu, Rile
%Y Haddow, Barry
%Y Kocmi, Tom
%Y Koehn, Philipp
%Y Monz, Christof
%S Proceedings of the Eleventh Conference on Machine Translation
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-474-3
%F yan-hu-2026-direction
%X We describe a lightweight system for the WMT26 Chinese-Southeast Asian Multilingual Translation Task, covering 14 directions between Chinese and seven Southeast Asian languages. It uses two independently trained Transformer Base models: a one-to-many (OTM) model for translation from Chinese and a many-to-one (MTO) model for translation into Chinese. Each model has 68,727,808 unique parameters. Both use 134,645 real parallel sentence pairs, augmented with 154,452 back-translated pairs for OTM and a 96,000-pair subset with synthetic Chinese targets for MTO. On the 6,859-pair internal test set, the final CTranslate2-based system achieves direction-family macro-average BLEU scores of 43.70 and 49.03; on the FLORES-200 crossdomain test set, they are 17.52 and 26.03, respectively. A CT2-only microbenchmark on a single NVIDIA GeForce RTX 5090 achieves 237.02 and 241.96 sentences per second on presegmented, source-length-stratified development samples, using the median of three steadystate measurements.
%U https://aclanthology.org/2026.wmt-main.183/
%P 2389-2396

Markdown (Informal)

[A Direction-Specialized System for WMT26 Chinese-Southeast Asian Multilingual Machine Translation](https://aclanthology.org/2026.wmt-main.183/) (Yan & Hu, WMT 2026)

• A Direction-Specialized System for WMT26 Chinese-Southeast Asian Multilingual Machine Translation (Yan & Hu, WMT 2026)

ACL

• Xiaojing Yan and Rile Hu. 2026. A Direction-Specialized System for WMT26 Chinese-Southeast Asian Multilingual Machine Translation. In Proceedings of the Eleventh Conference on Machine Translation, pages 2389–2396, Budapest, Hungary. Association for Computational Linguistics.