@inproceedings{maheshwari-nangi-2022-teamotter,
title = "{T}eam{O}tter at {S}em{E}val-2022 Task 5: Detecting Misogynistic Content in Multimodal Memes",
author = "Maheshwari, Paridhi and
Nangi, Sharmila Reddy",
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-1.88/",
doi = "10.18653/v1/2022.semeval-1.88",
pages = "642--647",
abstract = "We describe our system for the SemEval 2022 task on detecting misogynous content in memes. This is a pressing problem and we explore various methods ranging from traditional machine learning to deep learning models such as multimodal transformers. We propose a multimodal BERT architecture that uses information from both image and text. We further incorporate common world knowledge from pretrained CLIP and Urban dictionary. We also provide qualitative analysis to support out model. Our best performing model achieves an F1 score of 0.679 on Task A (Rank 5) and 0.680 on Task B (Rank 13) of the hidden test set. Our code is available at \url{https://github.com/paridhimaheshwari2708/MAMI}."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="maheshwari-nangi-2022-teamotter">
<titleInfo>
<title>TeamOtter at SemEval-2022 Task 5: Detecting Misogynistic Content in Multimodal Memes</title>
</titleInfo>
<name type="personal">
<namePart type="given">Paridhi</namePart>
<namePart type="family">Maheshwari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sharmila</namePart>
<namePart type="given">Reddy</namePart>
<namePart type="family">Nangi</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 describe our system for the SemEval 2022 task on detecting misogynous content in memes. This is a pressing problem and we explore various methods ranging from traditional machine learning to deep learning models such as multimodal transformers. We propose a multimodal BERT architecture that uses information from both image and text. We further incorporate common world knowledge from pretrained CLIP and Urban dictionary. We also provide qualitative analysis to support out model. Our best performing model achieves an F1 score of 0.679 on Task A (Rank 5) and 0.680 on Task B (Rank 13) of the hidden test set. Our code is available at https://github.com/paridhimaheshwari2708/MAMI.</abstract>
<identifier type="citekey">maheshwari-nangi-2022-teamotter</identifier>
<identifier type="doi">10.18653/v1/2022.semeval-1.88</identifier>
<location>
<url>https://aclanthology.org/2022.semeval-1.88/</url>
</location>
<part>
<date>2022-07</date>
<extent unit="page">
<start>642</start>
<end>647</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T TeamOtter at SemEval-2022 Task 5: Detecting Misogynistic Content in Multimodal Memes
%A Maheshwari, Paridhi
%A Nangi, Sharmila Reddy
%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 maheshwari-nangi-2022-teamotter
%X We describe our system for the SemEval 2022 task on detecting misogynous content in memes. This is a pressing problem and we explore various methods ranging from traditional machine learning to deep learning models such as multimodal transformers. We propose a multimodal BERT architecture that uses information from both image and text. We further incorporate common world knowledge from pretrained CLIP and Urban dictionary. We also provide qualitative analysis to support out model. Our best performing model achieves an F1 score of 0.679 on Task A (Rank 5) and 0.680 on Task B (Rank 13) of the hidden test set. Our code is available at https://github.com/paridhimaheshwari2708/MAMI.
%R 10.18653/v1/2022.semeval-1.88
%U https://aclanthology.org/2022.semeval-1.88/
%U https://doi.org/10.18653/v1/2022.semeval-1.88
%P 642-647
Markdown (Informal)
[TeamOtter at SemEval-2022 Task 5: Detecting Misogynistic Content in Multimodal Memes](https://aclanthology.org/2022.semeval-1.88/) (Maheshwari & Nangi, SemEval 2022)
ACL