<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhang-etal-2023-improving-multitask">
    <titleInfo>
        <title>Improving Multitask Retrieval by Promoting Task Specialization</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Wenzheng</namePart>
        <namePart type="family">Zhang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Chenyan</namePart>
        <namePart type="family">Xiong</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Karl</namePart>
        <namePart type="family">Stratos</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Arnold</namePart>
        <namePart type="family">Overwijk</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2023</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <genre authority="bibutilsgt">journal article</genre>
    <relatedItem type="host">
        <titleInfo>
            <title>Transactions of the Association for Computational Linguistics</title>
        </titleInfo>
        <originInfo>
            <issuance>continuing</issuance>
            <publisher>MIT Press</publisher>
            <place>
                <placeTerm type="text">Cambridge, MA</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">periodical</genre>
        <genre authority="bibutilsgt">academic journal</genre>
    </relatedItem>
    <abstract>In multitask retrieval, a single retriever is trained to retrieve relevant contexts for multiple tasks. Despite its practical appeal, naive multitask retrieval lags behind task-specific retrieval, in which a separate retriever is trained for each task. We show that it is possible to train a multitask retriever that outperforms task-specific retrievers by promoting task specialization. The main ingredients are: (1) a better choice of pretrained model—one that is explicitly optimized for multitasking—along with compatible prompting, and (2) a novel adaptive learning method that encourages each parameter to specialize in a particular task. The resulting multitask retriever is highly performant on the KILT benchmark. Upon analysis, we find that the model indeed learns parameters that are more task-specialized compared to naive multitasking without prompting or adaptive learning.1</abstract>
    <identifier type="citekey">zhang-etal-2023-improving-multitask</identifier>
    <identifier type="doi">10.1162/tacl_a_00597</identifier>
    <location>
        <url>https://aclanthology.org/2023.tacl-1.68</url>
    </location>
    <part>
        <date>2023</date>
        <detail type="volume"><number>11</number></detail>
        <extent unit="page">
            <start>1201</start>
            <end>1212</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Journal Article
%T Improving Multitask Retrieval by Promoting Task Specialization
%A Zhang, Wenzheng
%A Xiong, Chenyan
%A Stratos, Karl
%A Overwijk, Arnold
%J Transactions of the Association for Computational Linguistics
%D 2023
%V 11
%I MIT Press
%C Cambridge, MA
%F zhang-etal-2023-improving-multitask
%X In multitask retrieval, a single retriever is trained to retrieve relevant contexts for multiple tasks. Despite its practical appeal, naive multitask retrieval lags behind task-specific retrieval, in which a separate retriever is trained for each task. We show that it is possible to train a multitask retriever that outperforms task-specific retrievers by promoting task specialization. The main ingredients are: (1) a better choice of pretrained model—one that is explicitly optimized for multitasking—along with compatible prompting, and (2) a novel adaptive learning method that encourages each parameter to specialize in a particular task. The resulting multitask retriever is highly performant on the KILT benchmark. Upon analysis, we find that the model indeed learns parameters that are more task-specialized compared to naive multitasking without prompting or adaptive learning.1
%R 10.1162/tacl_a_00597
%U https://aclanthology.org/2023.tacl-1.68
%U https://doi.org/10.1162/tacl_a_00597
%P 1201-1212

Markdown (Informal)

[Improving Multitask Retrieval by Promoting Task Specialization](https://aclanthology.org/2023.tacl-1.68) (Zhang et al., TACL 2023)

• Improving Multitask Retrieval by Promoting Task Specialization (Zhang et al., TACL 2023)

ACL

• Wenzheng Zhang, Chenyan Xiong, Karl Stratos, and Arnold Overwijk. 2023. Improving Multitask Retrieval by Promoting Task Specialization. Transactions of the Association for Computational Linguistics, 11:1201–1212.