@inproceedings{singh-lefever-2021-lt3,
title = "{LT}3 at {S}em{E}val-2021 Task 6: Using Multi-Modal Compact Bilinear Pooling to Combine Visual and Textual Understanding in Memes",
author = "Singh, Pranaydeep and
Lefever, Els",
editor = "Palmer, Alexis and
Schneider, Nathan and
Schluter, Natalie and
Emerson, Guy and
Herbelot, Aurelie and
Zhu, Xiaodan",
booktitle = "Proceedings of the 15th International Workshop on Semantic Evaluation (SemEval-2021)",
month = aug,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.semeval-1.145",
doi = "10.18653/v1/2021.semeval-1.145",
pages = "1051--1055",
abstract = "Internet memes have become ubiquitous in social media networks today. Due to their popularity, they are also a widely used mode of expression to spread disinformation online. As memes consist of a mixture of text and image, they require a multi-modal approach for automatic analysis. In this paper, we describe our contribution to the SemEval-2021 Detection of Persuasian Techniques in Texts and Images Task. We propose a Multi-Modal learning system, which incorporates {``}memebeddings{''}, viz. joint text and vision features by combining them with compact bilinear pooling, to automatically identify rhetorical and psychological disinformation techniques. The experimental results show that the proposed system constantly outperforms the competition{'}s baseline, and achieves the 2nd best Macro F1-score and 14th best Micro F1-score out of all participants.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="singh-lefever-2021-lt3">
<titleInfo>
<title>LT3 at SemEval-2021 Task 6: Using Multi-Modal Compact Bilinear Pooling to Combine Visual and Textual Understanding in Memes</title>
</titleInfo>
<name type="personal">
<namePart type="given">Pranaydeep</namePart>
<namePart type="family">Singh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Els</namePart>
<namePart type="family">Lefever</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 15th International Workshop on Semantic Evaluation (SemEval-2021)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Alexis</namePart>
<namePart type="family">Palmer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nathan</namePart>
<namePart type="family">Schneider</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Natalie</namePart>
<namePart type="family">Schluter</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Guy</namePart>
<namePart type="family">Emerson</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aurelie</namePart>
<namePart type="family">Herbelot</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiaodan</namePart>
<namePart type="family">Zhu</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>Internet memes have become ubiquitous in social media networks today. Due to their popularity, they are also a widely used mode of expression to spread disinformation online. As memes consist of a mixture of text and image, they require a multi-modal approach for automatic analysis. In this paper, we describe our contribution to the SemEval-2021 Detection of Persuasian Techniques in Texts and Images Task. We propose a Multi-Modal learning system, which incorporates “memebeddings”, viz. joint text and vision features by combining them with compact bilinear pooling, to automatically identify rhetorical and psychological disinformation techniques. The experimental results show that the proposed system constantly outperforms the competition’s baseline, and achieves the 2nd best Macro F1-score and 14th best Micro F1-score out of all participants.</abstract>
<identifier type="citekey">singh-lefever-2021-lt3</identifier>
<identifier type="doi">10.18653/v1/2021.semeval-1.145</identifier>
<location>
<url>https://aclanthology.org/2021.semeval-1.145</url>
</location>
<part>
<date>2021-08</date>
<extent unit="page">
<start>1051</start>
<end>1055</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T LT3 at SemEval-2021 Task 6: Using Multi-Modal Compact Bilinear Pooling to Combine Visual and Textual Understanding in Memes
%A Singh, Pranaydeep
%A Lefever, Els
%Y Palmer, Alexis
%Y Schneider, Nathan
%Y Schluter, Natalie
%Y Emerson, Guy
%Y Herbelot, Aurelie
%Y Zhu, Xiaodan
%S Proceedings of the 15th International Workshop on Semantic Evaluation (SemEval-2021)
%D 2021
%8 August
%I Association for Computational Linguistics
%C Online
%F singh-lefever-2021-lt3
%X Internet memes have become ubiquitous in social media networks today. Due to their popularity, they are also a widely used mode of expression to spread disinformation online. As memes consist of a mixture of text and image, they require a multi-modal approach for automatic analysis. In this paper, we describe our contribution to the SemEval-2021 Detection of Persuasian Techniques in Texts and Images Task. We propose a Multi-Modal learning system, which incorporates “memebeddings”, viz. joint text and vision features by combining them with compact bilinear pooling, to automatically identify rhetorical and psychological disinformation techniques. The experimental results show that the proposed system constantly outperforms the competition’s baseline, and achieves the 2nd best Macro F1-score and 14th best Micro F1-score out of all participants.
%R 10.18653/v1/2021.semeval-1.145
%U https://aclanthology.org/2021.semeval-1.145
%U https://doi.org/10.18653/v1/2021.semeval-1.145
%P 1051-1055
Markdown (Informal)
[LT3 at SemEval-2021 Task 6: Using Multi-Modal Compact Bilinear Pooling to Combine Visual and Textual Understanding in Memes](https://aclanthology.org/2021.semeval-1.145) (Singh & Lefever, SemEval 2021)
ACL