@inproceedings{zhi-etal-2022-paic,
title = "{PAIC} at {S}em{E}val-2022 Task 5: Multi-Modal Misogynous Detection in {MEMES} with Multi-Task Learning And Multi-model Fusion",
author = "Zhi, Jin and
Mengyuan, Zhou and
Yuan, Mengfei and
Hu, Dou and
Du, Xiyang and
Jiang, Lianxin and
Mo, Yang and
Shi, XiaoFeng",
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-1.76/",
doi = "10.18653/v1/2022.semeval-1.76",
pages = "555--562",
abstract = "This paper describes our system used in the SemEval-2022 Task 5: Multimedia Automatic Misogyny Identification (MAMI). Multimedia automatic misogyny recognition consists of the identification of misogynous memes, taking advantage of both text and images as sources of information. The task will be organized around two main subtasks: Task A is a binary classification task, which should be identified either as misogynous or not misogynous. Task B is a multi-label classification task, in which the types of misogyny should be identified in potential overlapping categories, such as stereotype, shaming, objectification, and violence. In this paper, we proposed a system based on multi-task learning for multi-modal misogynous detection in memes. Our system combined image features with text features to train a multi-label classification. The prediction results were obtained by the simple weighted average method of the results with different fusion models, and the results of Task A were corrected by Task B. Our system achieves a test accuracy of 0.755 on Task A (ranking 3rd on the final leaderboard) and the accuracy of 0.731 on Task B (ranking 1st on the final leaderboard)."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhi-etal-2022-paic">
<titleInfo>
<title>PAIC at SemEval-2022 Task 5: Multi-Modal Misogynous Detection in MEMES with Multi-Task Learning And Multi-model Fusion</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jin</namePart>
<namePart type="family">Zhi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhou</namePart>
<namePart type="family">Mengyuan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mengfei</namePart>
<namePart type="family">Yuan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dou</namePart>
<namePart type="family">Hu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiyang</namePart>
<namePart type="family">Du</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lianxin</namePart>
<namePart type="family">Jiang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yang</namePart>
<namePart type="family">Mo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">XiaoFeng</namePart>
<namePart type="family">Shi</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>This paper describes our system used in the SemEval-2022 Task 5: Multimedia Automatic Misogyny Identification (MAMI). Multimedia automatic misogyny recognition consists of the identification of misogynous memes, taking advantage of both text and images as sources of information. The task will be organized around two main subtasks: Task A is a binary classification task, which should be identified either as misogynous or not misogynous. Task B is a multi-label classification task, in which the types of misogyny should be identified in potential overlapping categories, such as stereotype, shaming, objectification, and violence. In this paper, we proposed a system based on multi-task learning for multi-modal misogynous detection in memes. Our system combined image features with text features to train a multi-label classification. The prediction results were obtained by the simple weighted average method of the results with different fusion models, and the results of Task A were corrected by Task B. Our system achieves a test accuracy of 0.755 on Task A (ranking 3rd on the final leaderboard) and the accuracy of 0.731 on Task B (ranking 1st on the final leaderboard).</abstract>
<identifier type="citekey">zhi-etal-2022-paic</identifier>
<identifier type="doi">10.18653/v1/2022.semeval-1.76</identifier>
<location>
<url>https://aclanthology.org/2022.semeval-1.76/</url>
</location>
<part>
<date>2022-07</date>
<extent unit="page">
<start>555</start>
<end>562</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T PAIC at SemEval-2022 Task 5: Multi-Modal Misogynous Detection in MEMES with Multi-Task Learning And Multi-model Fusion
%A Zhi, Jin
%A Mengyuan, Zhou
%A Yuan, Mengfei
%A Hu, Dou
%A Du, Xiyang
%A Jiang, Lianxin
%A Mo, Yang
%A Shi, XiaoFeng
%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 zhi-etal-2022-paic
%X This paper describes our system used in the SemEval-2022 Task 5: Multimedia Automatic Misogyny Identification (MAMI). Multimedia automatic misogyny recognition consists of the identification of misogynous memes, taking advantage of both text and images as sources of information. The task will be organized around two main subtasks: Task A is a binary classification task, which should be identified either as misogynous or not misogynous. Task B is a multi-label classification task, in which the types of misogyny should be identified in potential overlapping categories, such as stereotype, shaming, objectification, and violence. In this paper, we proposed a system based on multi-task learning for multi-modal misogynous detection in memes. Our system combined image features with text features to train a multi-label classification. The prediction results were obtained by the simple weighted average method of the results with different fusion models, and the results of Task A were corrected by Task B. Our system achieves a test accuracy of 0.755 on Task A (ranking 3rd on the final leaderboard) and the accuracy of 0.731 on Task B (ranking 1st on the final leaderboard).
%R 10.18653/v1/2022.semeval-1.76
%U https://aclanthology.org/2022.semeval-1.76/
%U https://doi.org/10.18653/v1/2022.semeval-1.76
%P 555-562
Markdown (Informal)
[PAIC at SemEval-2022 Task 5: Multi-Modal Misogynous Detection in MEMES with Multi-Task Learning And Multi-model Fusion](https://aclanthology.org/2022.semeval-1.76/) (Zhi et al., SemEval 2022)
ACL
- Jin Zhi, Zhou Mengyuan, Mengfei Yuan, Dou Hu, Xiyang Du, Lianxin Jiang, Yang Mo, and XiaoFeng Shi. 2022. PAIC at SemEval-2022 Task 5: Multi-Modal Misogynous Detection in MEMES with Multi-Task Learning And Multi-model Fusion. In Proceedings of the 16th International Workshop on Semantic Evaluation (SemEval-2022), pages 555–562, Seattle, United States. Association for Computational Linguistics.