<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="guan-whitehill-2026-transformer">
    <titleInfo>
        <title>Transformer-Encoder Trees for Efficient Multilingual Machine Translation and Speech Translation</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Yiwen</namePart>
        <namePart type="family">Guan</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Jacob</namePart>
        <namePart type="family">Whitehill</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>Findings of the Association for Computational Linguistics: EMNLP 2026</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Hung-Yi</namePart>
            <namePart type="family">Lee</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Sunipa</namePart>
            <namePart type="family">Dev</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Jessy</namePart>
            <namePart type="family">Li</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Desmond</namePart>
            <namePart type="family">Elliott</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">979-8-89176-462-0</identifier>
    </relatedItem>
    <abstract>Multilingual translation suffers from computational redundancy, especially when translating into multiple languages simultaneously. In addition, translation quality can suffer for low-resource languages. To address this, we introduce Transformer Encoder Tree (TET), a hierarchical, non-autoregressive encoder-only architecture trained with Connectionist Temporal Classification (CTC) for multilingual translation. TET shares intermediate representations among linguistically similar target languages, improving accuracy on low-resource languages while reducing computational redundancy and enabling the generation of all target languages in a single forward pass. TET eliminates the sequential bottleneck of autoregressive models and supports fully parallel decoding of all tokens across all target languages. Compared to a naive one-to-many multilingual design, TET reduces the total parameter count by 66% and lowers inference computation by 60%. In speech translation, combining TET with a non-autoregressive speech recognition backbone (Wav2Vec2) shows competitive translation quality compared to autoregressive systems while speeding up inference by approximately 7-14 \times.</abstract>
    <identifier type="citekey">guan-whitehill-2026-transformer</identifier>
    <location>
        <url>https://aclanthology.org/2026.findings-emnlp.434/</url>
    </location>
    <part>
        <date>2026-10</date>
        <extent unit="page">
            <start>9115</start>
            <end>9127</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Transformer-Encoder Trees for Efficient Multilingual Machine Translation and Speech Translation
%A Guan, Yiwen
%A Whitehill, Jacob
%Y Lee, Hung-Yi
%Y Dev, Sunipa
%Y Li, Jessy
%Y Elliott, Desmond
%S Findings of the Association for Computational Linguistics: EMNLP 2026
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-462-0
%F guan-whitehill-2026-transformer
%X Multilingual translation suffers from computational redundancy, especially when translating into multiple languages simultaneously. In addition, translation quality can suffer for low-resource languages. To address this, we introduce Transformer Encoder Tree (TET), a hierarchical, non-autoregressive encoder-only architecture trained with Connectionist Temporal Classification (CTC) for multilingual translation. TET shares intermediate representations among linguistically similar target languages, improving accuracy on low-resource languages while reducing computational redundancy and enabling the generation of all target languages in a single forward pass. TET eliminates the sequential bottleneck of autoregressive models and supports fully parallel decoding of all tokens across all target languages. Compared to a naive one-to-many multilingual design, TET reduces the total parameter count by 66% and lowers inference computation by 60%. In speech translation, combining TET with a non-autoregressive speech recognition backbone (Wav2Vec2) shows competitive translation quality compared to autoregressive systems while speeding up inference by approximately 7-14 \times.
%U https://aclanthology.org/2026.findings-emnlp.434/
%P 9115-9127

Markdown (Informal)

[Transformer-Encoder Trees for Efficient Multilingual Machine Translation and Speech Translation](https://aclanthology.org/2026.findings-emnlp.434/) (Guan & Whitehill, Findings 2026)

• Transformer-Encoder Trees for Efficient Multilingual Machine Translation and Speech Translation (Guan & Whitehill, Findings 2026)

ACL

• Yiwen Guan and Jacob Whitehill. 2026. Transformer-Encoder Trees for Efficient Multilingual Machine Translation and Speech Translation. In Findings of the Association for Computational Linguistics: EMNLP 2026, pages 9115–9127, Budapest, Hungary. Association for Computational Linguistics.