<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="chen-etal-2022-adaptershare">
    <titleInfo>
        <title>AdapterShare: Task Correlation Modeling with Adapter Differentiation</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Zhi</namePart>
        <namePart type="family">Chen</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Bei</namePart>
        <namePart type="family">Chen</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Lu</namePart>
        <namePart type="family">Chen</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Kai</namePart>
        <namePart type="family">Yu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Jian-Guang</namePart>
        <namePart type="family">Lou</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>Thanks to the development of pre-trained language models, multitask learning (MTL) methods achieve a great success in natural language understanding area.However, current MTL methods pay more attention to task selection or model design to fuse as much knowledge as possible, while intrinsic task correlation is often neglected. It is important to learn sharing strategy among multiple tasks rather than sharing everything.%The MTL model is directly shared among all the tasks. %For example, in traditional MTL methods, the last classification layers or the decoder layers are manually separated. More deeply, In this paper, we propose AdapterShare, an adapter differentiation method to explicitly model the task correlation among multiple tasks. AdapterShare is automatically learned based on the gradients on tiny held-out validation data. Compared to single-task learning and fully shared MTL methods, our proposed method obtains obvious performance improvement. Compared to the existing MTL method AdapterFusion, AdapterShare achieves absolute 1.90 average points improvement on five dialogue understanding tasks and 2.33 points gain on NLU tasks.</abstract>
    <identifier type="citekey">chen-etal-2022-adaptershare</identifier>
    <identifier type="doi">10.18653/v1/2022.emnlp-main.728</identifier>
    <location>
        <url>https://aclanthology.org/2022.emnlp-main.728</url>
    </location>
    <part>
        <date>2022-12</date>
        <extent unit="page">
            <start>10645</start>
            <end>10651</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T AdapterShare: Task Correlation Modeling with Adapter Differentiation
%A Chen, Zhi
%A Chen, Bei
%A Chen, Lu
%A Yu, Kai
%A Lou, Jian-Guang
%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 chen-etal-2022-adaptershare
%X Thanks to the development of pre-trained language models, multitask learning (MTL) methods achieve a great success in natural language understanding area.However, current MTL methods pay more attention to task selection or model design to fuse as much knowledge as possible, while intrinsic task correlation is often neglected. It is important to learn sharing strategy among multiple tasks rather than sharing everything.%The MTL model is directly shared among all the tasks. %For example, in traditional MTL methods, the last classification layers or the decoder layers are manually separated. More deeply, In this paper, we propose AdapterShare, an adapter differentiation method to explicitly model the task correlation among multiple tasks. AdapterShare is automatically learned based on the gradients on tiny held-out validation data. Compared to single-task learning and fully shared MTL methods, our proposed method obtains obvious performance improvement. Compared to the existing MTL method AdapterFusion, AdapterShare achieves absolute 1.90 average points improvement on five dialogue understanding tasks and 2.33 points gain on NLU tasks.
%R 10.18653/v1/2022.emnlp-main.728
%U https://aclanthology.org/2022.emnlp-main.728
%U https://doi.org/10.18653/v1/2022.emnlp-main.728
%P 10645-10651

Markdown (Informal)

[AdapterShare: Task Correlation Modeling with Adapter Differentiation](https://aclanthology.org/2022.emnlp-main.728) (Chen et al., EMNLP 2022)

• AdapterShare: Task Correlation Modeling with Adapter Differentiation (Chen et al., EMNLP 2022)

ACL

• Zhi Chen, Bei Chen, Lu Chen, Kai Yu, and Jian-Guang Lou. 2022. AdapterShare: Task Correlation Modeling with Adapter Differentiation. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pages 10645–10651, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics.