<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="mickus-etal-2024-attention">
    <titleInfo>
        <title>I Have an Attention Bridge to Sell You: Generalization Capabilities of Modular Translation Architectures</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Timothee</namePart>
        <namePart type="family">Mickus</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Raul</namePart>
        <namePart type="family">Vazquez</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Joseph</namePart>
        <namePart type="family">Attieh</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2024-06</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the Fifth Workshop on Insights from Negative Results in NLP</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Shabnam</namePart>
            <namePart type="family">Tafreshi</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Arjun</namePart>
            <namePart type="family">Akula</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">João</namePart>
            <namePart type="family">Sedoc</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Aleksandr</namePart>
            <namePart type="family">Drozd</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Anna</namePart>
            <namePart type="family">Rogers</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Anna</namePart>
            <namePart type="family">Rumshisky</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Mexico City, Mexico</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Modularity is a paradigm of machine translation with the potential of bringing forth models that are large at training time and small during inference. Within this field of study, modular approaches, and in particular attention bridges, have been argued to improve the generalization capabilities of models by fostering language-independent representations. In the present paper, we study whether modularity affects translation quality; as well as how well modular architectures generalize across different evaluation scenarios. For a given computational budget, we find non-modular architectures to be always comparable or preferable to all modular designs we study.</abstract>
    <identifier type="citekey">mickus-etal-2024-attention</identifier>
    <identifier type="doi">10.18653/v1/2024.insights-1.5</identifier>
    <location>
        <url>https://aclanthology.org/2024.insights-1.5</url>
    </location>
    <part>
        <date>2024-06</date>
        <extent unit="page">
            <start>34</start>
            <end>40</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T I Have an Attention Bridge to Sell You: Generalization Capabilities of Modular Translation Architectures
%A Mickus, Timothee
%A Vazquez, Raul
%A Attieh, Joseph
%Y Tafreshi, Shabnam
%Y Akula, Arjun
%Y Sedoc, João
%Y Drozd, Aleksandr
%Y Rogers, Anna
%Y Rumshisky, Anna
%S Proceedings of the Fifth Workshop on Insights from Negative Results in NLP
%D 2024
%8 June
%I Association for Computational Linguistics
%C Mexico City, Mexico
%F mickus-etal-2024-attention
%X Modularity is a paradigm of machine translation with the potential of bringing forth models that are large at training time and small during inference. Within this field of study, modular approaches, and in particular attention bridges, have been argued to improve the generalization capabilities of models by fostering language-independent representations. In the present paper, we study whether modularity affects translation quality; as well as how well modular architectures generalize across different evaluation scenarios. For a given computational budget, we find non-modular architectures to be always comparable or preferable to all modular designs we study.
%R 10.18653/v1/2024.insights-1.5
%U https://aclanthology.org/2024.insights-1.5
%U https://doi.org/10.18653/v1/2024.insights-1.5
%P 34-40

Markdown (Informal)

[I Have an Attention Bridge to Sell You: Generalization Capabilities of Modular Translation Architectures](https://aclanthology.org/2024.insights-1.5) (Mickus et al., insights-WS 2024)

• I Have an Attention Bridge to Sell You: Generalization Capabilities of Modular Translation Architectures (Mickus et al., insights-WS 2024)

ACL

• Timothee Mickus, Raul Vazquez, and Joseph Attieh. 2024. I Have an Attention Bridge to Sell You: Generalization Capabilities of Modular Translation Architectures. In Proceedings of the Fifth Workshop on Insights from Negative Results in NLP, pages 34–40, Mexico City, Mexico. Association for Computational Linguistics.