@inproceedings{saioni-giannone-2024-multimodal,
title = "Multimodal Attention Is All You Need",
author = "Saioni, Marco and
Giannone, Cristina",
editor = "Dell'Orletta, Felice and
Lenci, Alessandro and
Montemagni, Simonetta and
Sprugnoli, Rachele",
booktitle = "Proceedings of the 10th Italian Conference on Computational Linguistics (CLiC-it 2024)",
month = dec,
year = "2024",
address = "Pisa, Italy",
publisher = "CEUR Workshop Proceedings",
url = "https://aclanthology.org/2024.clicit-1.94/",
pages = "873--879",
ISBN = "979-12-210-7060-6",
abstract = "In this paper, we present a multimodal model for classifying fake news. The main peculiarity of the proposed model is the \textit{cross attention} mechanism. Cross-attention is an evolution of the attention mechanism that allows the model to examine intermodal relationships to better understand information from different modalities, enabling it to simultaneously focus on the relevant parts of the data extracted from each. We tested the model using \textit{MULTI-Fake-DetectiVE} data from Evalita 2023. The presented model is particularly effective in both the tasks of classifying fake news and evaluating the intermodal relationship."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="saioni-giannone-2024-multimodal">
<titleInfo>
<title>Multimodal Attention Is All You Need</title>
</titleInfo>
<name type="personal">
<namePart type="given">Marco</namePart>
<namePart type="family">Saioni</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Cristina</namePart>
<namePart type="family">Giannone</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 10th Italian Conference on Computational Linguistics (CLiC-it 2024)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Felice</namePart>
<namePart type="family">Dell’Orletta</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alessandro</namePart>
<namePart type="family">Lenci</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Simonetta</namePart>
<namePart type="family">Montemagni</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rachele</namePart>
<namePart type="family">Sprugnoli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>CEUR Workshop Proceedings</publisher>
<place>
<placeTerm type="text">Pisa, Italy</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-12-210-7060-6</identifier>
</relatedItem>
<abstract>In this paper, we present a multimodal model for classifying fake news. The main peculiarity of the proposed model is the cross attention mechanism. Cross-attention is an evolution of the attention mechanism that allows the model to examine intermodal relationships to better understand information from different modalities, enabling it to simultaneously focus on the relevant parts of the data extracted from each. We tested the model using MULTI-Fake-DetectiVE data from Evalita 2023. The presented model is particularly effective in both the tasks of classifying fake news and evaluating the intermodal relationship.</abstract>
<identifier type="citekey">saioni-giannone-2024-multimodal</identifier>
<location>
<url>https://aclanthology.org/2024.clicit-1.94/</url>
</location>
<part>
<date>2024-12</date>
<extent unit="page">
<start>873</start>
<end>879</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Multimodal Attention Is All You Need
%A Saioni, Marco
%A Giannone, Cristina
%Y Dell’Orletta, Felice
%Y Lenci, Alessandro
%Y Montemagni, Simonetta
%Y Sprugnoli, Rachele
%S Proceedings of the 10th Italian Conference on Computational Linguistics (CLiC-it 2024)
%D 2024
%8 December
%I CEUR Workshop Proceedings
%C Pisa, Italy
%@ 979-12-210-7060-6
%F saioni-giannone-2024-multimodal
%X In this paper, we present a multimodal model for classifying fake news. The main peculiarity of the proposed model is the cross attention mechanism. Cross-attention is an evolution of the attention mechanism that allows the model to examine intermodal relationships to better understand information from different modalities, enabling it to simultaneously focus on the relevant parts of the data extracted from each. We tested the model using MULTI-Fake-DetectiVE data from Evalita 2023. The presented model is particularly effective in both the tasks of classifying fake news and evaluating the intermodal relationship.
%U https://aclanthology.org/2024.clicit-1.94/
%P 873-879
Markdown (Informal)
[Multimodal Attention Is All You Need](https://aclanthology.org/2024.clicit-1.94/) (Saioni & Giannone, CLiC-it 2024)
ACL
- Marco Saioni and Cristina Giannone. 2024. Multimodal Attention Is All You Need. In Proceedings of the 10th Italian Conference on Computational Linguistics (CLiC-it 2024), pages 873–879, Pisa, Italy. CEUR Workshop Proceedings.