@inproceedings{muti-etal-2022-unibo,
title = "{U}ni{BO} at {S}em{E}val-2022 Task 5: A Multimodal bi-Transformer Approach to the Binary and Fine-grained Identification of Misogyny in Memes",
author = "Muti, Arianna and
Korre, Katerina and
Barr{\'o}n-Cede{\~n}o, Alberto",
editor = "Emerson, Guy and
Schluter, Natalie and
Stanovsky, Gabriel and
Kumar, Ritesh and
Palmer, Alexis and
Schneider, Nathan and
Singh, Siddharth and
Ratan, Shyam",
booktitle = "Proceedings of the 16th International Workshop on Semantic Evaluation (SemEval-2022)",
month = jul,
year = "2022",
address = "Seattle, United States",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.semeval-1.91/",
doi = "10.18653/v1/2022.semeval-1.91",
pages = "663--672",
abstract = "We present our submission to SemEval 2022 Task 5 on Multimedia Automatic Misogyny Identification. We address the two tasks: Task A consists of identifying whether a meme is misogynous. If so, Task B attempts to identify its kind among shaming, stereotyping, objectification, and violence. Our approach combines a BERT Transformer with CLIP for the textual and visual representations. Both textual and visual encoders are fused in an early-fusion fashion through a Multimodal Bidirectional Transformer with unimodally pretrained components. Our official submissions obtain macro-averaged F$_1$=0.727 in Task A (4th position out of 69 participants)and weighted F$_1$=0.710 in Task B (4th position out of 42 participants)."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="muti-etal-2022-unibo">
<titleInfo>
<title>UniBO at SemEval-2022 Task 5: A Multimodal bi-Transformer Approach to the Binary and Fine-grained Identification of Misogyny in Memes</title>
</titleInfo>
<name type="personal">
<namePart type="given">Arianna</namePart>
<namePart type="family">Muti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Katerina</namePart>
<namePart type="family">Korre</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alberto</namePart>
<namePart type="family">Barrón-Cedeño</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 16th International Workshop on Semantic Evaluation (SemEval-2022)</title>
</titleInfo>
<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">Natalie</namePart>
<namePart type="family">Schluter</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gabriel</namePart>
<namePart type="family">Stanovsky</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ritesh</namePart>
<namePart type="family">Kumar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<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">Siddharth</namePart>
<namePart type="family">Singh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shyam</namePart>
<namePart type="family">Ratan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Seattle, United States</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We present our submission to SemEval 2022 Task 5 on Multimedia Automatic Misogyny Identification. We address the two tasks: Task A consists of identifying whether a meme is misogynous. If so, Task B attempts to identify its kind among shaming, stereotyping, objectification, and violence. Our approach combines a BERT Transformer with CLIP for the textual and visual representations. Both textual and visual encoders are fused in an early-fusion fashion through a Multimodal Bidirectional Transformer with unimodally pretrained components. Our official submissions obtain macro-averaged F₁=0.727 in Task A (4th position out of 69 participants)and weighted F₁=0.710 in Task B (4th position out of 42 participants).</abstract>
<identifier type="citekey">muti-etal-2022-unibo</identifier>
<identifier type="doi">10.18653/v1/2022.semeval-1.91</identifier>
<location>
<url>https://aclanthology.org/2022.semeval-1.91/</url>
</location>
<part>
<date>2022-07</date>
<extent unit="page">
<start>663</start>
<end>672</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T UniBO at SemEval-2022 Task 5: A Multimodal bi-Transformer Approach to the Binary and Fine-grained Identification of Misogyny in Memes
%A Muti, Arianna
%A Korre, Katerina
%A Barrón-Cedeño, Alberto
%Y Emerson, Guy
%Y Schluter, Natalie
%Y Stanovsky, Gabriel
%Y Kumar, Ritesh
%Y Palmer, Alexis
%Y Schneider, Nathan
%Y Singh, Siddharth
%Y Ratan, Shyam
%S Proceedings of the 16th International Workshop on Semantic Evaluation (SemEval-2022)
%D 2022
%8 July
%I Association for Computational Linguistics
%C Seattle, United States
%F muti-etal-2022-unibo
%X We present our submission to SemEval 2022 Task 5 on Multimedia Automatic Misogyny Identification. We address the two tasks: Task A consists of identifying whether a meme is misogynous. If so, Task B attempts to identify its kind among shaming, stereotyping, objectification, and violence. Our approach combines a BERT Transformer with CLIP for the textual and visual representations. Both textual and visual encoders are fused in an early-fusion fashion through a Multimodal Bidirectional Transformer with unimodally pretrained components. Our official submissions obtain macro-averaged F₁=0.727 in Task A (4th position out of 69 participants)and weighted F₁=0.710 in Task B (4th position out of 42 participants).
%R 10.18653/v1/2022.semeval-1.91
%U https://aclanthology.org/2022.semeval-1.91/
%U https://doi.org/10.18653/v1/2022.semeval-1.91
%P 663-672
Markdown (Informal)
[UniBO at SemEval-2022 Task 5: A Multimodal bi-Transformer Approach to the Binary and Fine-grained Identification of Misogyny in Memes](https://aclanthology.org/2022.semeval-1.91/) (Muti et al., SemEval 2022)
ACL