SubmissionNumber#=%=#45
FinalPaperTitle#=%=#NCL Team at SemEval-2024 Task 3: Fusing Multimodal Pre-training Embeddings for Emotion Cause Prediction in Conversations
ShortPaperTitle#=%=#
NumberOfPages#=%=#6
CopyrightSigned#=%=#Shu Li
JobTitle#==#
Organization#==#organization Name: Beijing Accent Advertising Co., Ltd.
Address: Beijing Shi Chaoyang Qu Qiangtai Xiang Dong Bajianfang Cun Beigangzi Dahuan Nei Jia 5 Hao Yuan

organization2:
Name: School of Computing, Newcastle University, Newcastle upon Tyne, UK
Address: Newcastle Newcastle University Newcastle upon Tyne NE1 7RU
Abstract#==#In this study, we introduce an MLP approach for extracting multimodal cause utterances in conversations, utilizing the multimodal conversational emotion causes from the ECF dataset. 
Our research focuses on evaluating a bi-modal framework that integrates video and audio embeddings to analyze emotional expressions within dialogues. 
The core of our methodology involves the extraction of embeddings from pre-trained models for each modality, followed by their concatenation and subsequent classification via an MLP network. We compared the accuracy performances across different modality combinations including text-audio-video, video-audio, and audio only.
Author{1}{Firstname}#=%=#Shu
Author{1}{Lastname}#=%=#Li
Author{1}{Username}#=%=#bbgame
Author{1}{Email}#=%=#15510388836@163.com
Author{1}{Affiliation}#=%=#Beijing Accent Advertising Co., Ltd.
Author{2}{Firstname}#=%=#Zicen
Author{2}{Lastname}#=%=#Liao
Author{2}{Email}#=%=#liaozicen55@gmail.com
Author{2}{Affiliation}#=%=#School of Computing, Newcastle University, Newcastle upon Tyne, UK
Author{3}{Firstname}#=%=#Huizhi
Author{3}{Lastname}#=%=#Liang
Author{3}{Email}#=%=#huizhi.liang@newcastle.ac.uk
Author{3}{Affiliation}#=%=#School of Computing, Newcastle University, Newcastle upon Tyne, UK

==========
èéáğö