@inproceedings{rao-rao-2022-asrtrans,
title = "{ASR}trans at {S}em{E}val-2022 Task 5: Transformer-based Models for Meme Classification",
author = "Rao, Ailneni Rakshitha and
Rao, Arjun",
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-1.82/",
doi = "10.18653/v1/2022.semeval-1.82",
pages = "597--604",
abstract = "Women are frequently targeted online with hate speech and misogyny using tweets, memes, and other forms of communication. This paper describes our system for Task 5 of SemEval-2022: Multimedia Automatic Misogyny Identification (MAMI). We participated in both the sub-tasks, where we used transformer-based architecture to combine features of images and text. We explore models with multi-modal pre-training (VisualBERT) and text-based pre-training (MMBT) while drawing comparative results. We also show how additional training with task-related external data can improve the model performance. We achieved sizable improvements over baseline models and the official evaluation ranked our system $3^{rd}$ out of 83 teams on the binary classification task (Sub-task A) with an F1 score of 0.761, and $7^{th}$ out of 48 teams on the multi-label classification task (Sub-task B) with an F1 score of 0.705."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="rao-rao-2022-asrtrans">
<titleInfo>
<title>ASRtrans at SemEval-2022 Task 5: Transformer-based Models for Meme Classification</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ailneni</namePart>
<namePart type="given">Rakshitha</namePart>
<namePart type="family">Rao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Arjun</namePart>
<namePart type="family">Rao</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>Women are frequently targeted online with hate speech and misogyny using tweets, memes, and other forms of communication. This paper describes our system for Task 5 of SemEval-2022: Multimedia Automatic Misogyny Identification (MAMI). We participated in both the sub-tasks, where we used transformer-based architecture to combine features of images and text. We explore models with multi-modal pre-training (VisualBERT) and text-based pre-training (MMBT) while drawing comparative results. We also show how additional training with task-related external data can improve the model performance. We achieved sizable improvements over baseline models and the official evaluation ranked our system 3^rd out of 83 teams on the binary classification task (Sub-task A) with an F1 score of 0.761, and 7^th out of 48 teams on the multi-label classification task (Sub-task B) with an F1 score of 0.705.</abstract>
<identifier type="citekey">rao-rao-2022-asrtrans</identifier>
<identifier type="doi">10.18653/v1/2022.semeval-1.82</identifier>
<location>
<url>https://aclanthology.org/2022.semeval-1.82/</url>
</location>
<part>
<date>2022-07</date>
<extent unit="page">
<start>597</start>
<end>604</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T ASRtrans at SemEval-2022 Task 5: Transformer-based Models for Meme Classification
%A Rao, Ailneni Rakshitha
%A Rao, Arjun
%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 rao-rao-2022-asrtrans
%X Women are frequently targeted online with hate speech and misogyny using tweets, memes, and other forms of communication. This paper describes our system for Task 5 of SemEval-2022: Multimedia Automatic Misogyny Identification (MAMI). We participated in both the sub-tasks, where we used transformer-based architecture to combine features of images and text. We explore models with multi-modal pre-training (VisualBERT) and text-based pre-training (MMBT) while drawing comparative results. We also show how additional training with task-related external data can improve the model performance. We achieved sizable improvements over baseline models and the official evaluation ranked our system 3^rd out of 83 teams on the binary classification task (Sub-task A) with an F1 score of 0.761, and 7^th out of 48 teams on the multi-label classification task (Sub-task B) with an F1 score of 0.705.
%R 10.18653/v1/2022.semeval-1.82
%U https://aclanthology.org/2022.semeval-1.82/
%U https://doi.org/10.18653/v1/2022.semeval-1.82
%P 597-604
Markdown (Informal)
[ASRtrans at SemEval-2022 Task 5: Transformer-based Models for Meme Classification](https://aclanthology.org/2022.semeval-1.82/) (Rao & Rao, SemEval 2022)
ACL