<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="mueller-etal-2022-text">
    <titleInfo>
        <title>Do Text-to-Text Multi-Task Learners Suffer from Task Conflict?</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">David</namePart>
        <namePart type="family">Mueller</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Nicholas</namePart>
        <namePart type="family">Andrews</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Mark</namePart>
        <namePart type="family">Dredze</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>Findings of the Association for Computational Linguistics: EMNLP 2022</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>Traditional multi-task learning architectures learn a single model across multiple tasks through a shared encoder followed by task-specific decoders. Learning these models often requires specialized training algorithms that address task-conflict in the shared parameter updates, which otherwise can lead to negative transfer. A new type of multi-task learning within NLP homogenizes multi-task architectures as a shared encoder and language model decoder, which does surprisingly well across a range of diverse tasks. Does this new architecture suffer from task-conflicts that require specialized training algorithms? We study how certain factors in the shift towards text-to-text models affects multi-task conflict and negative transfer, finding that both directional conflict and transfer are surprisingly constant across architectures.</abstract>
    <identifier type="citekey">mueller-etal-2022-text</identifier>
    <identifier type="doi">10.18653/v1/2022.findings-emnlp.206</identifier>
    <location>
        <url>https://aclanthology.org/2022.findings-emnlp.206</url>
    </location>
    <part>
        <date>2022-12</date>
        <extent unit="page">
            <start>2843</start>
            <end>2858</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Do Text-to-Text Multi-Task Learners Suffer from Task Conflict?
%A Mueller, David
%A Andrews, Nicholas
%A Dredze, Mark
%Y Goldberg, Yoav
%Y Kozareva, Zornitsa
%Y Zhang, Yue
%S Findings of the Association for Computational Linguistics: EMNLP 2022
%D 2022
%8 December
%I Association for Computational Linguistics
%C Abu Dhabi, United Arab Emirates
%F mueller-etal-2022-text
%X Traditional multi-task learning architectures learn a single model across multiple tasks through a shared encoder followed by task-specific decoders. Learning these models often requires specialized training algorithms that address task-conflict in the shared parameter updates, which otherwise can lead to negative transfer. A new type of multi-task learning within NLP homogenizes multi-task architectures as a shared encoder and language model decoder, which does surprisingly well across a range of diverse tasks. Does this new architecture suffer from task-conflicts that require specialized training algorithms? We study how certain factors in the shift towards text-to-text models affects multi-task conflict and negative transfer, finding that both directional conflict and transfer are surprisingly constant across architectures.
%R 10.18653/v1/2022.findings-emnlp.206
%U https://aclanthology.org/2022.findings-emnlp.206
%U https://doi.org/10.18653/v1/2022.findings-emnlp.206
%P 2843-2858

Markdown (Informal)

[Do Text-to-Text Multi-Task Learners Suffer from Task Conflict?](https://aclanthology.org/2022.findings-emnlp.206) (Mueller et al., Findings 2022)

• Do Text-to-Text Multi-Task Learners Suffer from Task Conflict? (Mueller et al., Findings 2022)

ACL

• David Mueller, Nicholas Andrews, and Mark Dredze. 2022. Do Text-to-Text Multi-Task Learners Suffer from Task Conflict?. In Findings of the Association for Computational Linguistics: EMNLP 2022, pages 2843–2858, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics.