@inproceedings{cheng-etal-2024-mips,
title = "{MIPS} at {S}em{E}val-2024 Task 3: Multimodal Emotion-Cause Pair Extraction in Conversations with Multimodal Language Models",
author = "Cheng, Zebang and
Niu, Fuqiang and
Lin, Yuxiang and
Cheng, Zhi-qi and
Peng, Xiaojiang and
Zhang, Bowen",
editor = {Ojha, Atul Kr. and
Do{\u{g}}ru{\"o}z, A. Seza and
Tayyar Madabushi, Harish and
Da San Martino, Giovanni and
Rosenthal, Sara and
Ros{\'a}, Aiala},
booktitle = "Proceedings of the 18th International Workshop on Semantic Evaluation (SemEval-2024)",
month = jun,
year = "2024",
address = "Mexico City, Mexico",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.semeval-1.97/",
doi = "10.18653/v1/2024.semeval-1.97",
pages = "667--674",
abstract = "This paper presents our winning submission to Subtask 2 of SemEval 2024 Task 3 on multimodal emotion cause analysis in conversations. We propose a novel Multimodal Emotion Recognition and Multimodal Emotion Cause Extraction (MER-MCE) framework that integrates text, audio, and visual modalities using specialized emotion encoders. Our approach sets itself apart from top-performing teams by leveraging modality-specific features for enhanced emotion understanding and causality inference. Experimental evaluation demonstrates the advantages of our multimodal approach, with our submission achieving a competitive weighted F1 score of 0.3435, ranking third with a margin of only 0.0339 behind the 1st team and 0.0025 behind the 2nd team."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="cheng-etal-2024-mips">
<titleInfo>
<title>MIPS at SemEval-2024 Task 3: Multimodal Emotion-Cause Pair Extraction in Conversations with Multimodal Language Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Zebang</namePart>
<namePart type="family">Cheng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fuqiang</namePart>
<namePart type="family">Niu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yuxiang</namePart>
<namePart type="family">Lin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhi-qi</namePart>
<namePart type="family">Cheng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiaojiang</namePart>
<namePart type="family">Peng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bowen</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 18th International Workshop on Semantic Evaluation (SemEval-2024)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Atul</namePart>
<namePart type="given">Kr.</namePart>
<namePart type="family">Ojha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">A</namePart>
<namePart type="given">Seza</namePart>
<namePart type="family">Doğruöz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Harish</namePart>
<namePart type="family">Tayyar Madabushi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Giovanni</namePart>
<namePart type="family">Da San Martino</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sara</namePart>
<namePart type="family">Rosenthal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aiala</namePart>
<namePart type="family">Rosá</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Mexico City, Mexico</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper presents our winning submission to Subtask 2 of SemEval 2024 Task 3 on multimodal emotion cause analysis in conversations. We propose a novel Multimodal Emotion Recognition and Multimodal Emotion Cause Extraction (MER-MCE) framework that integrates text, audio, and visual modalities using specialized emotion encoders. Our approach sets itself apart from top-performing teams by leveraging modality-specific features for enhanced emotion understanding and causality inference. Experimental evaluation demonstrates the advantages of our multimodal approach, with our submission achieving a competitive weighted F1 score of 0.3435, ranking third with a margin of only 0.0339 behind the 1st team and 0.0025 behind the 2nd team.</abstract>
<identifier type="citekey">cheng-etal-2024-mips</identifier>
<identifier type="doi">10.18653/v1/2024.semeval-1.97</identifier>
<location>
<url>https://aclanthology.org/2024.semeval-1.97/</url>
</location>
<part>
<date>2024-06</date>
<extent unit="page">
<start>667</start>
<end>674</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T MIPS at SemEval-2024 Task 3: Multimodal Emotion-Cause Pair Extraction in Conversations with Multimodal Language Models
%A Cheng, Zebang
%A Niu, Fuqiang
%A Lin, Yuxiang
%A Cheng, Zhi-qi
%A Peng, Xiaojiang
%A Zhang, Bowen
%Y Ojha, Atul Kr.
%Y Doğruöz, A. Seza
%Y Tayyar Madabushi, Harish
%Y Da San Martino, Giovanni
%Y Rosenthal, Sara
%Y Rosá, Aiala
%S Proceedings of the 18th International Workshop on Semantic Evaluation (SemEval-2024)
%D 2024
%8 June
%I Association for Computational Linguistics
%C Mexico City, Mexico
%F cheng-etal-2024-mips
%X This paper presents our winning submission to Subtask 2 of SemEval 2024 Task 3 on multimodal emotion cause analysis in conversations. We propose a novel Multimodal Emotion Recognition and Multimodal Emotion Cause Extraction (MER-MCE) framework that integrates text, audio, and visual modalities using specialized emotion encoders. Our approach sets itself apart from top-performing teams by leveraging modality-specific features for enhanced emotion understanding and causality inference. Experimental evaluation demonstrates the advantages of our multimodal approach, with our submission achieving a competitive weighted F1 score of 0.3435, ranking third with a margin of only 0.0339 behind the 1st team and 0.0025 behind the 2nd team.
%R 10.18653/v1/2024.semeval-1.97
%U https://aclanthology.org/2024.semeval-1.97/
%U https://doi.org/10.18653/v1/2024.semeval-1.97
%P 667-674
Markdown (Informal)
[MIPS at SemEval-2024 Task 3: Multimodal Emotion-Cause Pair Extraction in Conversations with Multimodal Language Models](https://aclanthology.org/2024.semeval-1.97/) (Cheng et al., SemEval 2024)
ACL