<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="hazman-etal-2023-unimodal">
    <titleInfo>
        <title>Unimodal Intermediate Training for Multimodal Meme Sentiment Classification</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Muzhaffar</namePart>
        <namePart type="family">Hazman</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Susan</namePart>
        <namePart type="family">McKeever</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Josephine</namePart>
        <namePart type="family">Griffith</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2023-09</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 14th International Conference on Recent Advances in Natural Language Processing</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Ruslan</namePart>
            <namePart type="family">Mitkov</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Galia</namePart>
            <namePart type="family">Angelova</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>INCOMA Ltd., Shoumen, Bulgaria</publisher>
            <place>
                <placeTerm type="text">Varna, Bulgaria</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Internet Memes remain a challenging form of user-generated content for automated sentiment classification. The availability of labelled memes is a barrier to developing sentiment classifiers of multimodal memes. To address the shortage of labelled memes, we propose to supplement the training of a multimodal meme classifier with unimodal (image-only and text-only) data. In this work, we present a novel variant of supervised intermediate training that uses relatively abundant sentiment-labelled unimodal data. Our results show a statistically significant performance improvement from the incorporation of unimodal text data. Furthermore, we show that the training set of labelled memes can be reduced by 40% without reducing the performance of the downstream model.</abstract>
    <identifier type="citekey">hazman-etal-2023-unimodal</identifier>
    <location>
        <url>https://aclanthology.org/2023.ranlp-1.55</url>
    </location>
    <part>
        <date>2023-09</date>
        <extent unit="page">
            <start>494</start>
            <end>506</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Unimodal Intermediate Training for Multimodal Meme Sentiment Classification
%A Hazman, Muzhaffar
%A McKeever, Susan
%A Griffith, Josephine
%Y Mitkov, Ruslan
%Y Angelova, Galia
%S Proceedings of the 14th International Conference on Recent Advances in Natural Language Processing
%D 2023
%8 September
%I INCOMA Ltd., Shoumen, Bulgaria
%C Varna, Bulgaria
%F hazman-etal-2023-unimodal
%X Internet Memes remain a challenging form of user-generated content for automated sentiment classification. The availability of labelled memes is a barrier to developing sentiment classifiers of multimodal memes. To address the shortage of labelled memes, we propose to supplement the training of a multimodal meme classifier with unimodal (image-only and text-only) data. In this work, we present a novel variant of supervised intermediate training that uses relatively abundant sentiment-labelled unimodal data. Our results show a statistically significant performance improvement from the incorporation of unimodal text data. Furthermore, we show that the training set of labelled memes can be reduced by 40% without reducing the performance of the downstream model.
%U https://aclanthology.org/2023.ranlp-1.55
%P 494-506

Markdown (Informal)

[Unimodal Intermediate Training for Multimodal Meme Sentiment Classification](https://aclanthology.org/2023.ranlp-1.55) (Hazman et al., RANLP 2023)

• Unimodal Intermediate Training for Multimodal Meme Sentiment Classification (Hazman et al., RANLP 2023)

ACL

• Muzhaffar Hazman, Susan McKeever, and Josephine Griffith. 2023. Unimodal Intermediate Training for Multimodal Meme Sentiment Classification. In Proceedings of the 14th International Conference on Recent Advances in Natural Language Processing, pages 494–506, Varna, Bulgaria. INCOMA Ltd., Shoumen, Bulgaria.