Saved in:
Bibliographic Details
Main Authors: Nguyen, Cam-Van Thi, Nguyen, Cao-Bach, Ha, Quang-Thuy, Le, Duc-Trong
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2402.17269
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913257515646976
author Nguyen, Cam-Van Thi
Nguyen, Cao-Bach
Ha, Quang-Thuy
Le, Duc-Trong
author_facet Nguyen, Cam-Van Thi
Nguyen, Cao-Bach
Ha, Quang-Thuy
Le, Duc-Trong
contents Emotion recognition in conversation (ERC) is a crucial task in natural language processing and affective computing. This paper proposes MultiDAG+CL, a novel approach for Multimodal Emotion Recognition in Conversation (ERC) that employs Directed Acyclic Graph (DAG) to integrate textual, acoustic, and visual features within a unified framework. The model is enhanced by Curriculum Learning (CL) to address challenges related to emotional shifts and data imbalance. Curriculum learning facilitates the learning process by gradually presenting training samples in a meaningful order, thereby improving the model's performance in handling emotional variations and data imbalance. Experimental results on the IEMOCAP and MELD datasets demonstrate that the MultiDAG+CL models outperform baseline models. We release the code for MultiDAG+CL and experiments: https://github.com/vanntc711/MultiDAG-CL
format Preprint
id arxiv_https___arxiv_org_abs_2402_17269
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Curriculum Learning Meets Directed Acyclic Graph for Multimodal Emotion Recognition
Nguyen, Cam-Van Thi
Nguyen, Cao-Bach
Ha, Quang-Thuy
Le, Duc-Trong
Machine Learning
Emotion recognition in conversation (ERC) is a crucial task in natural language processing and affective computing. This paper proposes MultiDAG+CL, a novel approach for Multimodal Emotion Recognition in Conversation (ERC) that employs Directed Acyclic Graph (DAG) to integrate textual, acoustic, and visual features within a unified framework. The model is enhanced by Curriculum Learning (CL) to address challenges related to emotional shifts and data imbalance. Curriculum learning facilitates the learning process by gradually presenting training samples in a meaningful order, thereby improving the model's performance in handling emotional variations and data imbalance. Experimental results on the IEMOCAP and MELD datasets demonstrate that the MultiDAG+CL models outperform baseline models. We release the code for MultiDAG+CL and experiments: https://github.com/vanntc711/MultiDAG-CL
title Curriculum Learning Meets Directed Acyclic Graph for Multimodal Emotion Recognition
topic Machine Learning
url https://arxiv.org/abs/2402.17269