<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="rao-vijjini-etal-2021-analyzing">
    <titleInfo>
        <title>Analyzing Curriculum Learning for Sentiment Analysis along Task Difficulty, Pacing and Visualization Axes</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Anvesh</namePart>
        <namePart type="family">Rao Vijjini</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Kaveri</namePart>
        <namePart type="family">Anuranjana</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Radhika</namePart>
        <namePart type="family">Mamidi</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2021-04</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the Eleventh Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Orphee</namePart>
            <namePart type="family">De Clercq</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Alexandra</namePart>
            <namePart type="family">Balahur</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Joao</namePart>
            <namePart type="family">Sedoc</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Valentin</namePart>
            <namePart type="family">Barriere</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <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">Sven</namePart>
            <namePart type="family">Buechel</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Veronique</namePart>
            <namePart type="family">Hoste</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Online</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>While Curriculum Learning (CL) has recently gained traction in Natural language Processing Tasks, it is still not adequately analyzed. Previous works only show their effectiveness but fail short to explain and interpret the internal workings fully. In this paper, we analyze curriculum learning in sentiment analysis along multiple axes. Some of these axes have been proposed by earlier works that need more in-depth study. Such analysis requires understanding where curriculum learning works and where it does not. Our axes of analysis include Task difficulty on CL, comparing CL pacing techniques, and qualitative analysis by visualizing the movement of attention scores in the model as curriculum phases progress. We find that curriculum learning works best for difficult tasks and may even lead to a decrement in performance for tasks with higher performance without curriculum learning. We see that One-Pass curriculum strategies suffer from catastrophic forgetting and attention movement visualization within curriculum pacing. This shows that curriculum learning breaks down the challenging main task into easier sub-tasks solved sequentially.</abstract>
    <identifier type="citekey">rao-vijjini-etal-2021-analyzing</identifier>
    <location>
        <url>https://aclanthology.org/2021.wassa-1.13</url>
    </location>
    <part>
        <date>2021-04</date>
        <extent unit="page">
            <start>117</start>
            <end>128</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Analyzing Curriculum Learning for Sentiment Analysis along Task Difficulty, Pacing and Visualization Axes
%A Rao Vijjini, Anvesh
%A Anuranjana, Kaveri
%A Mamidi, Radhika
%Y De Clercq, Orphee
%Y Balahur, Alexandra
%Y Sedoc, Joao
%Y Barriere, Valentin
%Y Tafreshi, Shabnam
%Y Buechel, Sven
%Y Hoste, Veronique
%S Proceedings of the Eleventh Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis
%D 2021
%8 April
%I Association for Computational Linguistics
%C Online
%F rao-vijjini-etal-2021-analyzing
%X While Curriculum Learning (CL) has recently gained traction in Natural language Processing Tasks, it is still not adequately analyzed. Previous works only show their effectiveness but fail short to explain and interpret the internal workings fully. In this paper, we analyze curriculum learning in sentiment analysis along multiple axes. Some of these axes have been proposed by earlier works that need more in-depth study. Such analysis requires understanding where curriculum learning works and where it does not. Our axes of analysis include Task difficulty on CL, comparing CL pacing techniques, and qualitative analysis by visualizing the movement of attention scores in the model as curriculum phases progress. We find that curriculum learning works best for difficult tasks and may even lead to a decrement in performance for tasks with higher performance without curriculum learning. We see that One-Pass curriculum strategies suffer from catastrophic forgetting and attention movement visualization within curriculum pacing. This shows that curriculum learning breaks down the challenging main task into easier sub-tasks solved sequentially.
%U https://aclanthology.org/2021.wassa-1.13
%P 117-128

Markdown (Informal)

[Analyzing Curriculum Learning for Sentiment Analysis along Task Difficulty, Pacing and Visualization Axes](https://aclanthology.org/2021.wassa-1.13) (Rao Vijjini et al., WASSA 2021)

• Analyzing Curriculum Learning for Sentiment Analysis along Task Difficulty, Pacing and Visualization Axes (Rao Vijjini et al., WASSA 2021)

ACL

• Anvesh Rao Vijjini, Kaveri Anuranjana, and Radhika Mamidi. 2021. Analyzing Curriculum Learning for Sentiment Analysis along Task Difficulty, Pacing and Visualization Axes. In Proceedings of the Eleventh Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis, pages 117–128, Online. Association for Computational Linguistics.