<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="duquenne-etal-2022-modules">
    <titleInfo>
        <title>T-Modules: Translation Modules for Zero-Shot Cross-Modal Machine Translation</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Paul-Ambroise</namePart>
        <namePart type="family">Duquenne</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Hongyu</namePart>
        <namePart type="family">Gong</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Benoît</namePart>
        <namePart type="family">Sagot</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Holger</namePart>
        <namePart type="family">Schwenk</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2022-12</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Yoav</namePart>
            <namePart type="family">Goldberg</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Zornitsa</namePart>
            <namePart type="family">Kozareva</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Yue</namePart>
            <namePart type="family">Zhang</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Abu Dhabi, United Arab Emirates</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>We present a new approach to perform zero-shot cross-modal transfer between speech and text for translation tasks. Multilingual speech and text are encoded in a joint fixed-size representation space. Then, we compare different approaches to decode these multimodal and multilingual fixed-size representations, enabling zero-shot translation between languages and modalities. All our models are trained without the need of cross-modal labeled translation data.Despite a fixed-size representation, we achieve very competitive results on several text and speech translation tasks. In particular, we significantly improve the state-of-the-art for zero-shot speech translation on Must-C. Incorporating a speech decoder in our framework, we introduce the first results for zero-shot direct speech-to-speech and text-to-speech translation.</abstract>
    <identifier type="citekey">duquenne-etal-2022-modules</identifier>
    <identifier type="doi">10.18653/v1/2022.emnlp-main.391</identifier>
    <location>
        <url>https://aclanthology.org/2022.emnlp-main.391</url>
    </location>
    <part>
        <date>2022-12</date>
        <extent unit="page">
            <start>5794</start>
            <end>5806</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T T-Modules: Translation Modules for Zero-Shot Cross-Modal Machine Translation
%A Duquenne, Paul-Ambroise
%A Gong, Hongyu
%A Sagot, Benoît
%A Schwenk, Holger
%Y Goldberg, Yoav
%Y Kozareva, Zornitsa
%Y Zhang, Yue
%S Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing
%D 2022
%8 December
%I Association for Computational Linguistics
%C Abu Dhabi, United Arab Emirates
%F duquenne-etal-2022-modules
%X We present a new approach to perform zero-shot cross-modal transfer between speech and text for translation tasks. Multilingual speech and text are encoded in a joint fixed-size representation space. Then, we compare different approaches to decode these multimodal and multilingual fixed-size representations, enabling zero-shot translation between languages and modalities. All our models are trained without the need of cross-modal labeled translation data.Despite a fixed-size representation, we achieve very competitive results on several text and speech translation tasks. In particular, we significantly improve the state-of-the-art for zero-shot speech translation on Must-C. Incorporating a speech decoder in our framework, we introduce the first results for zero-shot direct speech-to-speech and text-to-speech translation.
%R 10.18653/v1/2022.emnlp-main.391
%U https://aclanthology.org/2022.emnlp-main.391
%U https://doi.org/10.18653/v1/2022.emnlp-main.391
%P 5794-5806

Markdown (Informal)

[T-Modules: Translation Modules for Zero-Shot Cross-Modal Machine Translation](https://aclanthology.org/2022.emnlp-main.391) (Duquenne et al., EMNLP 2022)

• T-Modules: Translation Modules for Zero-Shot Cross-Modal Machine Translation (Duquenne et al., EMNLP 2022)

ACL

• Paul-Ambroise Duquenne, Hongyu Gong, Benoît Sagot, and Holger Schwenk. 2022. T-Modules: Translation Modules for Zero-Shot Cross-Modal Machine Translation. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pages 5794–5806, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics.