@inproceedings{baloun-etal-2024-uwba,
title = "{UWBA} at {S}em{E}val-2024 Task 3: Dialogue Representation and Multimodal Fusion for Emotion Cause Analysis",
author = "Baloun, Josef and
Martinek, Jiri and
Lenc, Ladislav and
Kral, Pavel and
Zeman, Mat{\v{e}}j and
Vl{\v{c}}ek, Luk{\'a}{\v{s}}",
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-1.49",
doi = "10.18653/v1/2024.semeval-1.49",
pages = "316--325",
abstract = "In this paper, we present an approach for solving SemEval-2024 Task 3: The Competition of Multimodal Emotion Cause Analysis in Conversations. The task includes two subtasks that focus on emotion-cause pair extraction using text, video, and audio modalities. Our approach is composed of encoding all modalities (MFCC and Wav2Vec for audio, 3D-CNN for video, and transformer-based models for text) and combining them in an utterance-level fusion module. The model is then optimized for link and emotion prediction simultaneously. Our approach achieved 6th place in both subtasks. The full leaderboard can be found at https://codalab.lisn.upsaclay.fr/competitions/16141{\#}results",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="baloun-etal-2024-uwba">
<titleInfo>
<title>UWBA at SemEval-2024 Task 3: Dialogue Representation and Multimodal Fusion for Emotion Cause Analysis</title>
</titleInfo>
<name type="personal">
<namePart type="given">Josef</namePart>
<namePart type="family">Baloun</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiri</namePart>
<namePart type="family">Martinek</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ladislav</namePart>
<namePart type="family">Lenc</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pavel</namePart>
<namePart type="family">Kral</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Matěj</namePart>
<namePart type="family">Zeman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lukáš</namePart>
<namePart type="family">Vlček</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>In this paper, we present an approach for solving SemEval-2024 Task 3: The Competition of Multimodal Emotion Cause Analysis in Conversations. The task includes two subtasks that focus on emotion-cause pair extraction using text, video, and audio modalities. Our approach is composed of encoding all modalities (MFCC and Wav2Vec for audio, 3D-CNN for video, and transformer-based models for text) and combining them in an utterance-level fusion module. The model is then optimized for link and emotion prediction simultaneously. Our approach achieved 6th place in both subtasks. The full leaderboard can be found at https://codalab.lisn.upsaclay.fr/competitions/16141#results</abstract>
<identifier type="citekey">baloun-etal-2024-uwba</identifier>
<identifier type="doi">10.18653/v1/2024.semeval-1.49</identifier>
<location>
<url>https://aclanthology.org/2024.semeval-1.49</url>
</location>
<part>
<date>2024-06</date>
<extent unit="page">
<start>316</start>
<end>325</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T UWBA at SemEval-2024 Task 3: Dialogue Representation and Multimodal Fusion for Emotion Cause Analysis
%A Baloun, Josef
%A Martinek, Jiri
%A Lenc, Ladislav
%A Kral, Pavel
%A Zeman, Matěj
%A Vlček, Lukáš
%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 baloun-etal-2024-uwba
%X In this paper, we present an approach for solving SemEval-2024 Task 3: The Competition of Multimodal Emotion Cause Analysis in Conversations. The task includes two subtasks that focus on emotion-cause pair extraction using text, video, and audio modalities. Our approach is composed of encoding all modalities (MFCC and Wav2Vec for audio, 3D-CNN for video, and transformer-based models for text) and combining them in an utterance-level fusion module. The model is then optimized for link and emotion prediction simultaneously. Our approach achieved 6th place in both subtasks. The full leaderboard can be found at https://codalab.lisn.upsaclay.fr/competitions/16141#results
%R 10.18653/v1/2024.semeval-1.49
%U https://aclanthology.org/2024.semeval-1.49
%U https://doi.org/10.18653/v1/2024.semeval-1.49
%P 316-325
Markdown (Informal)
[UWBA at SemEval-2024 Task 3: Dialogue Representation and Multimodal Fusion for Emotion Cause Analysis](https://aclanthology.org/2024.semeval-1.49) (Baloun et al., SemEval 2024)
ACL