@inproceedings{han-etal-2022-ynu,
title = "{YNU}-{HPCC} at {S}em{E}val-2022 Task 5: Multi-Modal and Multi-label Emotion Classification Based on {LXMERT}",
author = "Han, Chao and
Wang, Jin and
Zhang, Xuejie",
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-1.104/",
doi = "10.18653/v1/2022.semeval-1.104",
pages = "748--755",
abstract = "This paper describes our system used in the SemEval-2022 Task5 Multimedia Automatic Misogyny Identification (MAMI). This task is to use the provided text-image pairs to classify emotions. In this paper, We propose a multi-label emotion classification model based on pre-trained LXMERT. We use Faster-RCNN to extract visual representation and utilize LXMERT`s cross-attention for multi-modal alignment. Then we use the Bilinear-interaction layer to fuse these features. Our experimental results surpass the $F_1$ score of baseline. For Sub-task A, our $F_1$ score is 0.662 and Sub-task B`s $F_1$ score is 0.633. The code of this study is available on GitHub."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="han-etal-2022-ynu">
<titleInfo>
<title>YNU-HPCC at SemEval-2022 Task 5: Multi-Modal and Multi-label Emotion Classification Based on LXMERT</title>
</titleInfo>
<name type="personal">
<namePart type="given">Chao</namePart>
<namePart type="family">Han</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jin</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xuejie</namePart>
<namePart type="family">Zhang</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 Task5 Multimedia Automatic Misogyny Identification (MAMI). This task is to use the provided text-image pairs to classify emotions. In this paper, We propose a multi-label emotion classification model based on pre-trained LXMERT. We use Faster-RCNN to extract visual representation and utilize LXMERT‘s cross-attention for multi-modal alignment. Then we use the Bilinear-interaction layer to fuse these features. Our experimental results surpass the F₁ score of baseline. For Sub-task A, our F₁ score is 0.662 and Sub-task B‘s F₁ score is 0.633. The code of this study is available on GitHub.</abstract>
<identifier type="citekey">han-etal-2022-ynu</identifier>
<identifier type="doi">10.18653/v1/2022.semeval-1.104</identifier>
<location>
<url>https://aclanthology.org/2022.semeval-1.104/</url>
</location>
<part>
<date>2022-07</date>
<extent unit="page">
<start>748</start>
<end>755</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T YNU-HPCC at SemEval-2022 Task 5: Multi-Modal and Multi-label Emotion Classification Based on LXMERT
%A Han, Chao
%A Wang, Jin
%A Zhang, Xuejie
%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 han-etal-2022-ynu
%X This paper describes our system used in the SemEval-2022 Task5 Multimedia Automatic Misogyny Identification (MAMI). This task is to use the provided text-image pairs to classify emotions. In this paper, We propose a multi-label emotion classification model based on pre-trained LXMERT. We use Faster-RCNN to extract visual representation and utilize LXMERT‘s cross-attention for multi-modal alignment. Then we use the Bilinear-interaction layer to fuse these features. Our experimental results surpass the F₁ score of baseline. For Sub-task A, our F₁ score is 0.662 and Sub-task B‘s F₁ score is 0.633. The code of this study is available on GitHub.
%R 10.18653/v1/2022.semeval-1.104
%U https://aclanthology.org/2022.semeval-1.104/
%U https://doi.org/10.18653/v1/2022.semeval-1.104
%P 748-755
Markdown (Informal)
[YNU-HPCC at SemEval-2022 Task 5: Multi-Modal and Multi-label Emotion Classification Based on LXMERT](https://aclanthology.org/2022.semeval-1.104/) (Han et al., SemEval 2022)
ACL