@inproceedings{anghelina-etal-2024-sutealbastre,
title = "{S}ute{A}lbastre at {S}em{E}val-2024 Task 4: Predicting Propaganda Techniques in Multilingual Memes using Joint Text and Vision Transformers",
author = "Anghelina, Ion and
Bu{\textcommabelow{t}}{\u{a}}, Gabriel and
Enache, Alexandru",
editor = {Ojha, Atul Kr. and
Do{\u{g}}ru{\"o}z, A. Seza and
Tayyar Madabushi, Harish and
Da San Martino, Giovanni and
Rosenthal, Sara and
Ros{\'a}, Aiala},
booktitle = "Proceedings of the 18th International Workshop on Semantic Evaluation (SemEval-2024)",
month = jun,
year = "2024",
address = "Mexico City, Mexico",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.semeval-1.68",
doi = "10.18653/v1/2024.semeval-1.68",
pages = "443--449",
abstract = "The main goal of this year{'}s SemEval Task 4 isdetecting the presence of persuasion techniquesin various meme formats. While Subtask 1targets text-only posts, Subtask 2, subsectionsa and b tackle posts containing both imagesand captions. The first 2 subtasks consist ofmulti-class and multi-label classifications, inthe context of a hierarchical taxonomy of 22different persuasion techniques.This paper proposes a solution for persuasiondetection in both these scenarios and for vari-ous languages of the caption text. Our team{'}smain approach consists of a Multimodal Learn-ing Neural Network architecture, having Tex-tual and Vision Transformers as its backbone.The models that we have experimented with in-clude EfficientNet and ViT as visual encodersand BERT and GPT2 as textual encoders.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="anghelina-etal-2024-sutealbastre">
<titleInfo>
<title>SuteAlbastre at SemEval-2024 Task 4: Predicting Propaganda Techniques in Multilingual Memes using Joint Text and Vision Transformers</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ion</namePart>
<namePart type="family">Anghelina</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gabriel</namePart>
<namePart type="family">Bu\textcommabelowtă</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alexandru</namePart>
<namePart type="family">Enache</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 18th International Workshop on Semantic Evaluation (SemEval-2024)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Atul</namePart>
<namePart type="given">Kr.</namePart>
<namePart type="family">Ojha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">A</namePart>
<namePart type="given">Seza</namePart>
<namePart type="family">Doğruöz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Harish</namePart>
<namePart type="family">Tayyar Madabushi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Giovanni</namePart>
<namePart type="family">Da San Martino</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sara</namePart>
<namePart type="family">Rosenthal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aiala</namePart>
<namePart type="family">Rosá</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Mexico City, Mexico</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The main goal of this year’s SemEval Task 4 isdetecting the presence of persuasion techniquesin various meme formats. While Subtask 1targets text-only posts, Subtask 2, subsectionsa and b tackle posts containing both imagesand captions. The first 2 subtasks consist ofmulti-class and multi-label classifications, inthe context of a hierarchical taxonomy of 22different persuasion techniques.This paper proposes a solution for persuasiondetection in both these scenarios and for vari-ous languages of the caption text. Our team’smain approach consists of a Multimodal Learn-ing Neural Network architecture, having Tex-tual and Vision Transformers as its backbone.The models that we have experimented with in-clude EfficientNet and ViT as visual encodersand BERT and GPT2 as textual encoders.</abstract>
<identifier type="citekey">anghelina-etal-2024-sutealbastre</identifier>
<identifier type="doi">10.18653/v1/2024.semeval-1.68</identifier>
<location>
<url>https://aclanthology.org/2024.semeval-1.68</url>
</location>
<part>
<date>2024-06</date>
<extent unit="page">
<start>443</start>
<end>449</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T SuteAlbastre at SemEval-2024 Task 4: Predicting Propaganda Techniques in Multilingual Memes using Joint Text and Vision Transformers
%A Anghelina, Ion
%A Bu\textcommabelowtă, Gabriel
%A Enache, Alexandru
%Y Ojha, Atul Kr.
%Y Doğruöz, A. Seza
%Y Tayyar Madabushi, Harish
%Y Da San Martino, Giovanni
%Y Rosenthal, Sara
%Y Rosá, Aiala
%S Proceedings of the 18th International Workshop on Semantic Evaluation (SemEval-2024)
%D 2024
%8 June
%I Association for Computational Linguistics
%C Mexico City, Mexico
%F anghelina-etal-2024-sutealbastre
%X The main goal of this year’s SemEval Task 4 isdetecting the presence of persuasion techniquesin various meme formats. While Subtask 1targets text-only posts, Subtask 2, subsectionsa and b tackle posts containing both imagesand captions. The first 2 subtasks consist ofmulti-class and multi-label classifications, inthe context of a hierarchical taxonomy of 22different persuasion techniques.This paper proposes a solution for persuasiondetection in both these scenarios and for vari-ous languages of the caption text. Our team’smain approach consists of a Multimodal Learn-ing Neural Network architecture, having Tex-tual and Vision Transformers as its backbone.The models that we have experimented with in-clude EfficientNet and ViT as visual encodersand BERT and GPT2 as textual encoders.
%R 10.18653/v1/2024.semeval-1.68
%U https://aclanthology.org/2024.semeval-1.68
%U https://doi.org/10.18653/v1/2024.semeval-1.68
%P 443-449
Markdown (Informal)
[SuteAlbastre at SemEval-2024 Task 4: Predicting Propaganda Techniques in Multilingual Memes using Joint Text and Vision Transformers](https://aclanthology.org/2024.semeval-1.68) (Anghelina et al., SemEval 2024)
ACL