Curriculum Learning Meets Directed Acyclic Graph for Multimodal Emotion Recognition
This work addresses emotion recognition in conversation for natural language processing and affective computing applications, presenting an incremental improvement by combining existing techniques.
The paper tackles multimodal emotion recognition in conversation by proposing MultiDAG+CL, which integrates textual, acoustic, and visual features using a Directed Acyclic Graph and enhances it with Curriculum Learning to handle emotional shifts and data imbalance, resulting in outperforming baseline models on the IEMOCAP and MELD datasets.
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