<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="varshney-mishra-and-chitta-baral-2022-model">
    <titleInfo>
        <title>Let the Model Decide its Curriculum for Multitask Learning</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Neeraj</namePart>
        <namePart type="family">Varshney</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Swaroop</namePart>
        <namePart type="family">Mishra</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Chitta</namePart>
        <namePart type="family">Baral</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2022-07</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the Third Workshop on Deep Learning for Low-Resource Natural Language Processing</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Colin</namePart>
            <namePart type="family">Cherry</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Angela</namePart>
            <namePart type="family">Fan</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">George</namePart>
            <namePart type="family">Foster</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Gholamreza</namePart>
            <namePart type="given">(Reza)</namePart>
            <namePart type="family">Haffari</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Shahram</namePart>
            <namePart type="family">Khadivi</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Nanyun</namePart>
            <namePart type="given">(Violet)</namePart>
            <namePart type="family">Peng</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Xiang</namePart>
            <namePart type="family">Ren</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Ehsan</namePart>
            <namePart type="family">Shareghi</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Swabha</namePart>
            <namePart type="family">Swayamdipta</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Hybrid</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Curriculum learning strategies in prior multitask learning approaches arrange datasets in a difficulty hierarchy either based on human perception or by exhaustively searching the optimal arrangement. However, human perception of difficulty may not always correlate well with machine interpretation leading to poor performance and exhaustive search is computationally expensive. Addressing these concerns, we propose two classes of techniques to arrange training instances into a learning curriculum based on difficulty scores computed via model-based approaches. The two classes i.e Dataset-level and Instance-level differ in granularity of arrangement. Through comprehensive experiments with 12 datasets, we show that instance-level and dataset-level techniques result in strong representations as they lead to an average performance improvement of 4.17% and 3.15% over their respective baselines. Furthermore, we find that most of this improvement comes from correctly answering the difficult instances, implying a greater efficacy of our techniques on difficult tasks</abstract>
    <identifier type="citekey">varshney-mishra-and-chitta-baral-2022-model</identifier>
    <identifier type="doi">10.18653/v1/2022.deeplo-1.13</identifier>
    <location>
        <url>https://aclanthology.org/2022.deeplo-1.13</url>
    </location>
    <part>
        <date>2022-07</date>
        <extent unit="page">
            <start>117</start>
            <end>125</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Let the Model Decide its Curriculum for Multitask Learning
%A Varshney, Neeraj
%A Mishra, Swaroop
%A Baral, Chitta
%Y Cherry, Colin
%Y Fan, Angela
%Y Foster, George
%Y Haffari, Gholamreza (Reza)
%Y Khadivi, Shahram
%Y Peng, Nanyun (Violet)
%Y Ren, Xiang
%Y Shareghi, Ehsan
%Y Swayamdipta, Swabha
%S Proceedings of the Third Workshop on Deep Learning for Low-Resource Natural Language Processing
%D 2022
%8 July
%I Association for Computational Linguistics
%C Hybrid
%F varshney-mishra-and-chitta-baral-2022-model
%X Curriculum learning strategies in prior multitask learning approaches arrange datasets in a difficulty hierarchy either based on human perception or by exhaustively searching the optimal arrangement. However, human perception of difficulty may not always correlate well with machine interpretation leading to poor performance and exhaustive search is computationally expensive. Addressing these concerns, we propose two classes of techniques to arrange training instances into a learning curriculum based on difficulty scores computed via model-based approaches. The two classes i.e Dataset-level and Instance-level differ in granularity of arrangement. Through comprehensive experiments with 12 datasets, we show that instance-level and dataset-level techniques result in strong representations as they lead to an average performance improvement of 4.17% and 3.15% over their respective baselines. Furthermore, we find that most of this improvement comes from correctly answering the difficult instances, implying a greater efficacy of our techniques on difficult tasks
%R 10.18653/v1/2022.deeplo-1.13
%U https://aclanthology.org/2022.deeplo-1.13
%U https://doi.org/10.18653/v1/2022.deeplo-1.13
%P 117-125

Markdown (Informal)

[Let the Model Decide its Curriculum for Multitask Learning](https://aclanthology.org/2022.deeplo-1.13) (Varshney et al., DeepLo 2022)

• Let the Model Decide its Curriculum for Multitask Learning (Varshney et al., DeepLo 2022)

ACL

• Neeraj Varshney, Swaroop Mishra, and Chitta Baral. 2022. Let the Model Decide its Curriculum for Multitask Learning. In Proceedings of the Third Workshop on Deep Learning for Low-Resource Natural Language Processing, pages 117–125, Hybrid. Association for Computational Linguistics.