@inproceedings{li-etal-2022-ams,
title = "{AMS}{\_}{ADRN} at {S}em{E}val-2022 Task 5: A Suitable Image-text Multimodal Joint Modeling Method for Multi-task Misogyny Identification",
author = "Li, Da and
Yi, Ming and
He, Yukai",
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-1.97/",
doi = "10.18653/v1/2022.semeval-1.97",
pages = "711--717",
abstract = "Women are influential online, especially in image-based social media such as Twitter and Instagram. However, many in the network environment contain gender discrimination and aggressive information, which magnify gender stereotypes and gender inequality. Therefore, the filtering of illegal content such as gender discrimination is essential to maintain a healthy social network environment. In this paper, we describe the system developed by our team for SemEval-2022Task 5: Multimedia Automatic Misogyny Identification. More specifically, we introduce two novel system to analyze these posts: a multimodal multi-task learning architecture that combines Bertweet for text encoding with ResNet-18 for image representation, and a single-flow transformer structure which combines text embeddings from BERT-Embeddings and image embeddings from several different modules such as EfficientNet and ResNet. In this manner, we show that the information behind them can be properly revealed. Our approach achieves good performance on each of the two subtasks of the current competition, ranking 15th for Subtask A (0.746 macro F1-score), 11th for Subtask B (0.706 macro F1-score) while exceeding the official baseline results by high margins."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="li-etal-2022-ams">
<titleInfo>
<title>AMS_ADRN at SemEval-2022 Task 5: A Suitable Image-text Multimodal Joint Modeling Method for Multi-task Misogyny Identification</title>
</titleInfo>
<name type="personal">
<namePart type="given">Da</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ming</namePart>
<namePart type="family">Yi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yukai</namePart>
<namePart type="family">He</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 influential online, especially in image-based social media such as Twitter and Instagram. However, many in the network environment contain gender discrimination and aggressive information, which magnify gender stereotypes and gender inequality. Therefore, the filtering of illegal content such as gender discrimination is essential to maintain a healthy social network environment. In this paper, we describe the system developed by our team for SemEval-2022Task 5: Multimedia Automatic Misogyny Identification. More specifically, we introduce two novel system to analyze these posts: a multimodal multi-task learning architecture that combines Bertweet for text encoding with ResNet-18 for image representation, and a single-flow transformer structure which combines text embeddings from BERT-Embeddings and image embeddings from several different modules such as EfficientNet and ResNet. In this manner, we show that the information behind them can be properly revealed. Our approach achieves good performance on each of the two subtasks of the current competition, ranking 15th for Subtask A (0.746 macro F1-score), 11th for Subtask B (0.706 macro F1-score) while exceeding the official baseline results by high margins.</abstract>
<identifier type="citekey">li-etal-2022-ams</identifier>
<identifier type="doi">10.18653/v1/2022.semeval-1.97</identifier>
<location>
<url>https://aclanthology.org/2022.semeval-1.97/</url>
</location>
<part>
<date>2022-07</date>
<extent unit="page">
<start>711</start>
<end>717</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T AMS_ADRN at SemEval-2022 Task 5: A Suitable Image-text Multimodal Joint Modeling Method for Multi-task Misogyny Identification
%A Li, Da
%A Yi, Ming
%A He, Yukai
%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 li-etal-2022-ams
%X Women are influential online, especially in image-based social media such as Twitter and Instagram. However, many in the network environment contain gender discrimination and aggressive information, which magnify gender stereotypes and gender inequality. Therefore, the filtering of illegal content such as gender discrimination is essential to maintain a healthy social network environment. In this paper, we describe the system developed by our team for SemEval-2022Task 5: Multimedia Automatic Misogyny Identification. More specifically, we introduce two novel system to analyze these posts: a multimodal multi-task learning architecture that combines Bertweet for text encoding with ResNet-18 for image representation, and a single-flow transformer structure which combines text embeddings from BERT-Embeddings and image embeddings from several different modules such as EfficientNet and ResNet. In this manner, we show that the information behind them can be properly revealed. Our approach achieves good performance on each of the two subtasks of the current competition, ranking 15th for Subtask A (0.746 macro F1-score), 11th for Subtask B (0.706 macro F1-score) while exceeding the official baseline results by high margins.
%R 10.18653/v1/2022.semeval-1.97
%U https://aclanthology.org/2022.semeval-1.97/
%U https://doi.org/10.18653/v1/2022.semeval-1.97
%P 711-717
Markdown (Informal)
[AMS_ADRN at SemEval-2022 Task 5: A Suitable Image-text Multimodal Joint Modeling Method for Multi-task Misogyny Identification](https://aclanthology.org/2022.semeval-1.97/) (Li et al., SemEval 2022)
ACL