Curriculum Learning Meets Directed Acyclic Graph for Multimodal Emotion Recognition

TL;DR

This paper introduces MultiDAG+CL, a novel multimodal emotion recognition model that uses a DAG structure and curriculum learning to improve performance on conversational emotion datasets.

Contribution

It presents a new framework combining DAG and curriculum learning for multimodal ERC, addressing emotional shifts and data imbalance effectively.

Findings

Outperforms baseline models on IEMOCAP and MELD datasets

Demonstrates improved handling of emotional shifts and data imbalance

Provides publicly available code for reproducibility

Abstract

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